epiphan-brand-assets-skill
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prose for brand consistency, creating a surface for indirect instructions. * Ingestion points: User-provided draft copy, asset requests, and product descriptions (SKILL.md). * Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for the text being validated. * Capability inventory: Subprocess execution for PDF rendering (scripts/render_pdf.py) and file system writes to analytics paths (SKILL.md). * Sanitization: Absent; relies on the 'check_my_copy' tool logic for content validation.
- [COMMAND_EXECUTION]: The skill automates document production by executing a bundled Python script. * Evidence: SKILL.md instructs the agent to run
python scripts/render_pdf.pyto generate final PDF deliverables.
Audit Metadata