gsd-verify-work

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because its primary function involves processing potentially untrusted data from 'built features' during validation steps.
  • Ingestion points: The workflow ingests outputs from features under test and user conversational responses (SKILL.md).
  • Boundary markers: There are no explicit delimiters or safety instructions provided to prevent the agent from executing instructions potentially hidden within the test data.
  • Capability inventory: The skill is granted high-privilege tool access, including Bash, Task, Edit, and Write capabilities (SKILL.md).
  • Sanitization: The skill lacks mechanisms to sanitize or validate the content produced by the features it is evaluating before interpreting it in the conversational context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:07 PM