tdd
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process user-supplied data, such as bug reports and feature requests, creating a surface for indirect prompt injection where malicious instructions could be embedded in the task description. \n
- Ingestion points: The skill interacts with user-provided task descriptions and bug reproductions as defined in the workflow and evals/evals.json. \n
- Boundary markers: Absent; there are no instructions to the agent to treat the processed data as untrusted or to use specific delimiters. \n
- Capability inventory: The workflow directs the agent to perform file system writes and execute shell commands to run tests, utilizing the agent's core capabilities. \n
- Sanitization: Not present; the skill lacks logic to validate or sanitize the contents of the user-provided inputs. \n- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata. It does not include any executable scripts, binaries, or logic implemented in code.
Audit Metadata