repo-manager-reference

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a large surface area for repository operations through the gh-manager.js helper script. This includes high-impact actions such as deleting branches (branches delete), merging pull requests (prs merge), and modifying global configurations (config portfolio-write).
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its interaction with untrusted external data.
  • Ingestion points: Data enters the agent context through commands like gh-manager files get, gh-manager prs comments, gh-manager issues get, and gh-manager discussions list (SKILL.md).
  • Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands within the ingested data.
  • Capability inventory: The tool possesses significant write and administrative capabilities, including file writing/deletion, branch management, PR merging, and issue closure (SKILL.md).
  • Sanitization: No explicit sanitization or validation logic is mentioned for content retrieved from external repository sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:36 PM
Security Audit — agent-trust-hub — repo-manager-reference