piv-fix-review-findings
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via the
$reviewargument. - Ingestion points: The skill ingests untrusted data from the
$reviewargument, which can be the content of an external file. - Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard embedded directives within the review content.
- Capability inventory: The skill possesses significant capabilities, including the ability to modify local source code, execute tests, and perform git operations such as committing and pushing changes to a remote repository.
- Sanitization: The instructions do not specify any sanitization, validation, or escaping of the content provided in the review findings before it is processed by the agent.
Audit Metadata