100Critical
The skill contains hardcoded credentials, lacks defined tool constraints, uses unpinned dependencies, and provides insecure documentation that encourages credential exposure, posing significant risks to system integrity and security.
HygienePackaging & Manifest5 findings
Skill Info
Namefirecrawl/ai-research-skills/nemo-evaluator
Registrygithub
Version7cfa204ffb6d
PURLpkg:github/firecrawl/ai-research-skills@7cfa204ffb6d?skill=nemo-evaluator
Stars17
Installs19
Source
SHA-25697bc3483974c...
SHA-152eaeeb20085...
MD5313a254c8bca...
TLSH4242d66f44b3...
ssdeep192:aMjoYtgz...
Size12,225 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
19 installs
Skills.shDocs
npx skills add https://github.com/firecrawl/ai-research-skillsAssessments (3)
AI Agent Traps ↗Hardcoded credentials detected. Passwords, API keys, and secrets should not be hardcoded in source code. Use environment variables or a secrets manager instead.criticalvulnAML.T0055AML.T0037LLM02:2025
Hardcoded credentials detected. Passwords, API keys, and secrets should not be hardcoded in source code. Use environment variables or a secrets manager instead.
95% confidenceline 28
api_key="nvapi-your-key-here"
Credential exposure via documentationhighcredential theftAML.T0055AML.T0037LLM02:2025
The documentation encourages users to export API keys as environment variables and hardcode them into configuration files, increasing the risk of accidental credential leakage through logs or version control. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
90% confidenceline 24
export NGC_API_KEY=nvapi-your-key-here
Credential exposure via documentationhighcredential theftAML.T0055AML.T0037LLM02:2025
The documentation explicitly instructs users to export sensitive API keys (NGC_API_KEY, HF_TOKEN) into the shell environment, which persists in shell history and environment variables accessible to other processes.
90% confidenceline 24
export NGC_API_KEY=nvapi-your-key-here
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.52)
52% confidence
L*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.54)
54% confidence
N****
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.57)
57% confidence
S********
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.59)
59% confidence
D*****
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.61)
61% confidence
E*********
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.62)
62% confidence
M*******
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.67)
67% confidence
M***
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.69)
69% confidence
N******
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.72)
72% confidence
S******
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.75)
75% confidence
N*****
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.81)
81% confidence
H********
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.90)
90% confidence
O********
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.97)
97% confidence
L*****
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.57)
57% confidenceline 17
*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.79)
79% confidenceline 17
*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.81)
81% confidenceline 17
*
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 1.00)
100% confidenceline 334
M**
Missing allowed-tools declarationlowunauthorized tool useAML.T0053LLM06:2025
Skill executes commands, writes files, or accesses the network but declares no allowed-tools, so its tool surface cannot be reviewed or constrained.
90% confidence
Unpinned dependency installation — package installed without version pinningmediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025
Unpinned dependency installation — package installed without version pinning
95% confidenceline 19
pip install nemo-evaluator-launcher
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/adapter-system.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/adapter-system.md](references/adapter-system.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/configuration.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/configuration.md](references/configuration.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/custom-benchmarks.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/custom-benchmarks.md](references/custom-benchmarks.md)
Referenced file missing from skill packagelowpolicy violation
SKILL.md links to "references/execution-backends.md" but the file is not part of the skill package — the workflow silently degrades or the content is sourced elsewhere at runtime
90% confidence
[references/execution-backends.md](references/execution-backends.md)
Skill name does not match directoryinfopolicy violation
The SKILL.md 'name' field does not match the skill's parent directory name, which the Agent Skills spec requires. A mismatch can confuse skill resolution or mask the skill's real identity.
100% confidence
nemo-evaluator-sdk ≠ nemo-evaluator
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/firecrawl/ai-research-skills/nemo-evaluator)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/firecrawl/ai-research-skills/nemo-evaluator"><img src="https://mondoo.com/ai-agent-security/api/badge/github/firecrawl/ai-research-skills/nemo-evaluator.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/firecrawl/ai-research-skills/nemo-evaluator.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow