skills/yrzhe/claude-skills/learn/Gen Agent Trust Hub

learn

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it distills instructions from untrusted conversation history into new skill definitions. This risk is categorized as low due to embedded mitigations.
  • Ingestion points: Analyzes the current conversation history to identify core workflow steps and decisions for extraction.
  • Boundary markers: The instructions do not define explicit boundary markers or use 'ignore embedded instructions' warnings when parsing conversation data.
  • Capability inventory: The skill uses the 'Write' and 'Edit' tools to modify the agent's local environment in ~/.claude/skills/ and 'Bash' for searching operations.
  • Sanitization: Security is primarily enforced via a mandatory user confirmation step ('Write to disk only after confirmation'), which ensures that the user reviews any generated instructions before they are persisted.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 07:09 AM
Security Audit — agent-trust-hub — learn