copy-editing
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process untrusted text provided by the user for editing purposes, which introduces a surface for indirect prompt injection.
- Ingestion points: User-provided marketing copy and the
.claude/product-marketing-context.mdfile (SKILL.md). - Boundary markers: The skill does not define specific delimiters or instructions to ignore instructions embedded within the user copy.
- Capability inventory: Across all files (SKILL.md, scripts/readability_scorer.py), the skill is limited to text analysis and console output; it has no network access or file-system modification tools.
- Sanitization: The skill performs no validation or escaping of the user-provided text before processing.
- [COMMAND_EXECUTION]: The skill includes a local Python script (
scripts/readability_scorer.py) used to generate readability reports. - The script uses standard libraries and performs purely mathematical and regex-based analysis of the input text.
- It does not perform network operations, access sensitive files, or use dangerous functions like eval() or exec().
Audit Metadata