pr-complexity
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data such as Pull Request code and metadata, which introduces a surface for indirect prompt injection where instructions embedded in analyzed data could influence agent behavior.\n
- Ingestion points: The skill reads files and accesses data via Snowflake tools as specified in the Required Contract section of SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the content being analyzed.\n
- Capability inventory: The skill utilizes file operations (Read, Write, Edit), shell execution (Bash), and data access tools.\n
- Sanitization: No specific data sanitization or validation logic is mentioned for the processed artifacts.\n- [COMMAND_EXECUTION]: The instructions permit the use of Bash when explicitly required by the host to perform the complexity analysis logic. This is a standard capability for the intended use case and is scoped to the feature's requirements.
Audit Metadata