project-session-manager

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes standard system and development utilities such as git, tmux, jq, and flock. It also utilizes official platform CLIs including gh (GitHub), az (Azure), glab (GitLab), and jira to automate repository and issue management tasks.- [EXTERNAL_DOWNLOADS]: The skill communicates with well-known technology platforms (GitHub, GitLab, Bitbucket, Azure DevOps, Jira) to fetch metadata for pull requests and issues. These operations target established services and are integral to the skill's primary function of environment synchronization.- [PROMPT_INJECTION]: The skill presents a surface for Indirect Prompt Injection (Category 8) by ingesting untrusted data (PR and Issue bodies) from remote sources into the agent's context through generated markdown templates. While this is an inherent risk of its intended use case, the skill does not contain any instructions that attempt to override the agent's core safety guidelines.- [SAFE]: The implementation demonstrates strong defensive coding patterns, such as using flock for atomic state management and validate_worktree_path to prevent path traversal during worktree cleanup.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:43 AM
Security Audit — agent-trust-hub — project-session-manager