firstsun-pm

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to manage project items and repository state, including commands like gh issue create, gh project item-add, and gh pr create. It also specifies the execution of repository-level scripts for linting, building, and testing during the implementation workflow.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes user-provided task descriptions and repository content while maintaining the ability to execute shell commands and perform write operations to GitHub.
  • Ingestion points: User input for new tasks and descriptions in repository issues/PRs.
  • Boundary markers: None present to isolate processed data from instructions.
  • Capability inventory: Shell command execution via GitHub CLI and project build/lint/test scripts.
  • Sanitization: None present for user data interpolated into issue and PR descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:14 AM