write-copy
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Python script,
scripts/check_copy.py, to perform automated checks on the generated marketing copy. This script validates word counts, detects buzzwords, and ensures no invented numbers or testimonials are included.- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface because it ingests data from external sources such as README files, documentation, and websites. However, it mitigates this risk through strict grounding instructions (e.g., "never invents proof or urgency," "write only from facts") and a post-generation validation step using a script.- [EXTERNAL_DOWNLOADS]: The skill references an external sanitization tool (ai-sanitize) hosted on the author's GitHub repository (github.com/jeffabailey/skills). As this resource is owned by the skill's author, it represents expected functional dependency rather than a third-party supply chain risk.
Audit Metadata