gsd-add-tests
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project files to define test logic, creating a vulnerability surface where instructions embedded in data could be executed. 1. Ingestion points: The skill reads from SUMMARY.md, CONTEXT.md, VERIFICATION.md, .planning/STATE.md, and .planning/ROADMAP.md. 2. Boundary markers: No explicit delimiters or instructions are provided in the skill definition to separate these data sources from the agent's core instructions. 3. Capability inventory: The skill is permitted to use Bash, Write, Edit, and Task tools, which allow for file system modification and command execution. 4. Sanitization: No sanitization or validation of the input file content is described.
- [COMMAND_EXECUTION]: The skill is granted access to the Bash and Task tools to facilitate the execution and verification of generated tests. This access represents a significant capability that could be abused if the agent's instructions are influenced by malicious content within the analyzed files.
Audit Metadata