issue-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local files (
strategy/brand.md,about/me.md,CLAUDE.md) and user-provided text (prompts and outputs) to generate a report. While this constitutes an attack surface, the risk is negligible as the skill lacks capabilities for automated execution, network exfiltration, or privileged file operations. The process relies on user review of the generated markdown. - Ingestion points: Workspace files (SKILL.md Step 2) and user-supplied strings (SKILL.md Step 1).
- Boundary markers: Absent.
- Capability inventory: Text generation only; no subprocesses, network requests, or sensitive file writes.
- Sanitization: Absent.
- [EXTERNAL_DOWNLOADS]: The skill includes a link to the author's official GitHub repository (
github.com/manojbajaj95/claude-gtm-plugin) for filing bug reports. This is a standard and safe use of an external resource belonging to the skill's vendor.
Audit Metadata