skills/team-attention/hoyeon/clarify/Gen Agent Trust Hub

clarify

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill maintains an indirect prompt injection surface as it ingests untrusted data from the codebase and user input for processing by subagents.
  • Ingestion points: SKILL.md (Core Loop, step 4: 'Explore instead of asking' and step 5: 'Record immediately').
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when passing the qa-log.md to the 'clarity-auditor' subagent.
  • Capability inventory: The skill has access to potentially powerful tools including Bash, Read, Write, and Edit.
  • Sanitization: The skill does not define specific sanitization or filtering logic for the content read from the codebase or provided by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — clarify