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.md and .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, and Grep tools (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 Bash tool. 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
Risk Level
SAFE
Analyzed
Jul 11, 2026, 09:38 PM
Security Audit — agent-trust-hub — gsd-audit-uat