common-feedback-reporter
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by intercepting 'planned code' (derived from user requests) to verify compliance with loaded skill rules. This creates an indirect prompt injection surface where user-provided content could attempt to influence the agent's auditing and reporting logic.
- Ingestion points: Processes the agent's planned code output before it is written to files (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined for the 'Violation Report Format' block to separate rule text from the potentially untrusted code snippets.
- Capability inventory: The skill influences agent output blocks and gates file write operations like 'write_to_file' and 'replace_file_content'.
- Sanitization: There is no evidence of sanitization or escaping for the code snippets included in the violation report.
Audit Metadata