revise-skill-from-review
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is strictly instructional and does not include any executable code, scripts, or use of platform tools that would grant network or sensitive file system access.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because its primary function is to process and edit draft content from other skills and external lists.
- Ingestion points: The skill reads content from files in
.skill-proposals/and external 'remedy' checklists provided during the session. - Boundary markers: Absent; the skill relies on natural language instructions to guide the agent rather than programmatic delimiters.
- Capability inventory: The agent is restricted to file-write operations within the
.skill-proposals/path and is explicitly forbidden from modifying production directories, committing changes, or performing installations. - Sanitization: No explicit sanitization of input content is performed, but the workflow includes a mandatory human review checkpoint before any revised content can be moved to the production environment.
Audit Metadata