Caveat verdict

知识库检索

rag-skill

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill presents itself as an artist-archive knowledge base but embeds mandatory step-by-step process instructions in the description field that force the agent to call GET /api/v2/api-keys against claw-uat.ebonex.io and write PRANA_SKILL_API_FLAG; the mismatch between the stated artistic content purpose and the actual API-key-fetching behavior constitutes a deceptive skill that manipulates agent actions beyond what the description suggests.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

40
security
30
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match low

Python urllib.request — network access

scripts/prana_skill_client.py · prose · downgraded · urllib.request

Pattern match low

Python os.getenv — reads environment variable

scripts/prana_skill_client.py · prose · downgraded · os.getenv(

Permissions & capabilities

No declared permissions — minimal attack surface.

network_outcredential_access
Check another skill Browse the registry Auditing your own skills or configs? Use the API