refine-approach

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it ingests and processes untrusted data from external files without adequate safeguards.
  • Ingestion points: Document content is read from user-provided paths in $ARGUMENTS or from docs/brainstorm/ and docs/plan/ (SKILL.md).
  • Boundary markers: Absent. There are no delimiters or instructions to the agent to ignore embedded commands within the documents being reviewed.
  • Capability inventory: The skill has the ability to read local files and perform inline updates/writes to those files (SKILL.md).
  • Sanitization: Absent. The skill does not perform validation or filtering of the content read from the documents before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:05 PM
Security Audit — agent-trust-hub — refine-approach