setup-copywriting-md
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by instructing the agent to ingest and process data from untrusted external websites.
- Ingestion points: The agent is directed to research external patterns by visiting competitor homepages, pricing pages, and category leader websites as described in
SKILL.md(Step 2). - Boundary markers: There are no explicit instructions or delimiters provided to ensure the agent treats external web content strictly as data or ignores any malicious instructions that might be embedded in those third-party sites.
- Capability inventory: The skill grants the agent permission to write a new file (
COPYWRITING.md) and modify an existing project index file (AGENTS.md) based on the gathered research. - Sanitization: The workflow lacks requirements for sanitizing or validating the content retrieved from external URLs before it is interpolated into the generated documentation.
Audit Metadata