bug-hunter-security
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the analysis of external codebases.
- Ingestion points: The skill scans repositories and codebase content provided by the user (SKILL.md).
- Boundary markers: Absent. There are no delimiters or instructions provided to the agent to disregard instructions found within the data being analyzed.
- Capability inventory: The skill is capable of running "ad-hoc tests" and writing "automated test cases" (SKILL.md).
- Sanitization: Absent. The skill does not implement validation or escaping for the external content it processes.
- [COMMAND_EXECUTION]: The instruction to "Run ad-hoc tests to verify potential vulnerabilities" involves executing code or system commands. Since these tests are performed on untrusted codebases, an attacker could embed malicious instructions that the agent might execute while attempting to verify a faked vulnerability.
Audit Metadata