review-security-change
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content described as the 'supplied change scope'. This introduces a surface for indirect prompt injection attacks.
- Ingestion points: The skill processes external data defined in the 'supplied change scope' (SKILL.md).
- Boundary markers: There are no instructions specifying the use of delimiters or advice to ignore instructions found within the data being reviewed.
- Capability inventory: The skill does not request tools for network access, file system writes, or subprocess execution, which significantly reduces the risk of malicious payload execution.
- Sanitization: No sanitization, escaping, or validation of the external content is mentioned in the instructions.
Audit Metadata