gsd-audit-uat
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external markdown files located in
.planning/phases/. This creates an attack surface for indirect prompt injection where instructions embedded in these files could influence agent behavior. - Ingestion points:
.planning/phases/*/*-UAT.mdand.planning/phases/*/*-VERIFICATION.md(SKILL.md) - Boundary markers: Not present. No explicit instructions are provided to the agent to ignore content inside the scanned files.
- Capability inventory: The skill allows use of
Bash,Read,Glob, andGreptools (SKILL.md). - Sanitization: Not present. Content from the files is cross-referenced against the codebase without evident filtering.
- [COMMAND_EXECUTION]: The skill configuration allows the use of the
Bashtool. While standard for auditing tasks, this capability provides a mechanism for executing shell commands if the agent is successfully manipulated via injected instructions.
Audit Metadata