audit-verify-explain-grade-5
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's core workflow in
SKILL.mdinstructs the agent to execute arbitrary commands for verification purposes, including running automated tests, build systems, linters, and the actual application or workflow being audited. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its requirement to process untrusted data (code diffs, logs, and artifacts) while maintaining high-privilege tool access.
- Ingestion points: According to
SKILL.md, the agent ingests code diffs, touched files, call sites, existing tests, logs, and process checks. - Boundary markers: The instructions lack specific guidance for using delimiters or explicit warnings to ignore potential instructions embedded within the audited content.
- Capability inventory: The agent has broad capabilities to execute code via tests, builds, and application runs as defined in the 'Verify' section of
SKILL.md. - Sanitization: There is no evidence of sanitization or filtering logic to prevent malicious content in the input data from being interpreted as instructions.
Audit Metadata