skills/security-phoenix-demo/security-skills-claude-code/tm-quick-security-assessment/Gen Agent Trust Hub
tm-quick-security-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the file system and git repositories. Specifically, it executes
git worktree addandgit diff --name-onlyto scope its analysis to specific branches and changes. - [INDIRECT_PROMPT_INJECTION]: The skill represents a vulnerability surface as it ingests untrusted data from external sources.
- Ingestion points: The skill reads content from git diffs, changed files in a repository, and external threat model documents (
*-threat-model.md) provided by the user or found in the project. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing these external files.
- Capability inventory: The agent has the capability to execute shell commands (
git), read local files, and write report files to~/security-reviews/. - Sanitization: There are no explicit instructions for the agent to sanitize or escape content retrieved from the repository files before processing it.
- [EXTERNAL_DOWNLOADS]: The skill references sibling skills (
security-assessmentand0day-scanner) via relative file paths. While it does not download them from a remote URL in this file, it relies on their presence in the local environment.
Audit Metadata