skill-iterate
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes historical session logs and user feedback to modify skill instructions, creating a surface for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data from historical session logs via a local service (http://127.0.0.1:8390) and through user-provided failure reports.
- Boundary markers: The instructions do not include markers or warnings to isolate the agent from potentially malicious instructions embedded in the processed session data.
- Capability inventory: The skill possesses the ability to write to local configuration and instruction files (SKILL.md, plugin.json, README.md) and proposes Git commit commands for user approval.
- Sanitization: No sanitization or validation steps are prescribed for the ingested session data before it is used to update skill instructions.
Audit Metadata