verify-test
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's primary workflow involves executing builds and tests. This capability allows for the execution of system-level commands based on the provided verification plan.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted data from external sources.
- Ingestion points: The skill receives 'Issue or bead id', 'Verification plan', and 'Test commands' as inputs in
SKILL.md. - Boundary markers: There are no delimiters or instructions provided to the agent to treat input data as non-executable text or to ignore embedded instructions.
- Capability inventory: The skill possesses the capability to 'Execute builds/tests' (workflow step 2), which typically involves shell access.
- Sanitization: There is no evidence of input validation, escaping, or filtering for the 'Test commands' or 'Verification plan' inputs.
Audit Metadata