project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions
52
59%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./skills/project-session-manager/SKILL.mdSecurity
1 medium severity finding. This skill can be installed but you should review these findings before use.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill explicitly instructs launching Claude with the "--dangerously-skip-permissions" flag (via tmux sends), which bypasses interactive permission/tool-approval prompts and thus encourages circumventing host security mechanisms.
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
In `psm.sh` the required runtime workflow for `review <ref>`/`fix <ref>` fetches outsider-authored PR/issue text via `gh pr view ... --json ... body` and `gh issue view ... --json ... body` and then injects it into the LLM context file (`$worktree_path/.psm/review.md` / `$worktree_path/.psm/fix.md`) that Claude Code reads (via `psm_launch_claude` -> `psm_inject_prompt`).
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill fetches remote repository and PR/issue content at runtime (used to build the initial Claude prompt) via GitHub clone/fetch operations such as "https://github.com/$repo.git" / "https://github.com/${repo}.git", so external content from those URLs can directly influence the agent's prompts.
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
5aa678c
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.