tdd
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data (bug reports and source code) and perform command execution (running tests), which constitutes a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent processes user-provided codebase files and bug descriptions as specified in the workflow instructions in SKILL.md.
- Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded within the code or data being tested.
- Capability inventory: The skill requires the ability to execute commands to run tests, scripts, and manual reproduction steps as described in the "Workflow" and "If a Failing Test Is Impractical" sections.
- Sanitization: Absent. There are no guidelines or steps included to sanitize or validate external content before it is interpolated into test execution paths.
Audit Metadata