skills/paulund/ai/dev-implement/Gen Agent Trust Hub

dev-implement

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh CLI tools for routine development operations such as branching, viewing issue details, committing changes, and pushing code. These operations are aligned with the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and follows instructions derived from external, untrusted GitHub issue bodies.
  • Ingestion points: The gh issue view command in Step 1 and Step 3 retrieves issue titles and bodies from GitHub.
  • Boundary markers: There are no boundary markers or instructions provided to the agent to disregard potential commands embedded within the issue body.
  • Capability inventory: The skill has the capability to write to the local filesystem, commit changes, and push code to remote repositories.
  • Sanitization: No sanitization or validation of the issue content is performed before it is used to drive the TDD cycle.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 05:43 PM
Security Audit — agent-trust-hub — dev-implement