repository-governance-lifecycle

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use node -e to process and Base64-encode SVG assets for repository branding. It also utilizes a project-specific CLI command steward claim check to verify evidence against repository claims. These operations are standard for documentation and asset management workflows.\n- [EXTERNAL_DOWNLOADS]: Provides an installation path using npx to fetch the skill from the author's repository. This is a standard distribution method for this platform.\n- [PROMPT_INJECTION]: The skill processes untrusted external data such as 'task.md', 'implementation_plan.md', and various evidence artifacts, creating an attack surface for indirect prompt injection.\n
  • Ingestion points: Reads local task and plan files to extract context for ADRs and FAQs.\n
  • Boundary markers: Absent; there are no explicit instructions to use delimiters when processing these files.\n
  • Capability inventory: The skill has permissions to read/write files and execute the steward CLI.\n
  • Sanitization: No sanitization or input validation is specified for the content extracted from external files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 03:49 PM
Security Audit — agent-trust-hub — repository-governance-lifecycle