teardown-audit
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Step 2 instructs the agent to run
node <teardown>/kit/map.mjs <slug>. This shell command uses variables for both the script path and its arguments. The<slug>argument is explicitly allowed to be a 'published URL', which involves the local script processing external network data. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and audit project files such as code, drafts, and design documents, which are untrusted external inputs.
- Ingestion points: Project source files, notes, and external URLs provided as slugs (SKILL.md, Steps 1-2).
- Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore instructions found within the audited project files.
- Capability inventory: The skill possesses capabilities for command execution via
node(Step 2), file creation for reports (Step 7), and modification of existing teardown map files (Step 8). - Sanitization: Absent. The skill does not include steps to sanitize or validate the content of the project files before they are interpreted by the agent or written to reports.
Audit Metadata