coding-guidance-cpp
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes external, potentially untrusted data from a repository to perform coding and review tasks.
- Ingestion points: The 'Implementation Workflow' in
SKILL.mddirects the agent to read 'touched code, build shape, existing tests, and any nearby docs'. - Boundary markers: The skill does not define explicit delimiters or instructions to ignore instructions that might be embedded within the ingested repository content.
- Capability inventory: The skill utilizes tool execution for formatting, building, testing, and running sanitizers or analyzers as defined by the repository's build system (
SKILL.md). - Sanitization: No explicit sanitization or validation of the repository content is specified in the skill instructions before processing or execution.
Audit Metadata