static-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading source code, configuration files, and repository instructions to identify bugs. This creates an attack surface where an attacker could place malicious instructions within the code (e.g., in comments) to influence the agent's behavior during the analysis or when invoking the $add-issue tool. \n
- Ingestion points: Reads all code in the specified or default repository scope, including tests and configuration (SKILL.md). \n
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded prompts within the files being analyzed. \n
- Capability inventory: The skill is authorized to invoke the $add-issue tool to record findings. \n
- Sanitization: No sanitization or validation of the content extracted from source files is mentioned before it is passed to the downstream tool.
Audit Metadata