marketing-selling-point-generator
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation instructions direct users to clone a repository from an untrusted GitHub account (
danidai098-arch). This account does not match the stated author of the skill ("ara.so" or "reason-machines"), posing a supply chain risk where the downloaded code may differ from the documented behavior. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external user feedback which could contain malicious instructions designed to influence the AI's output.
- Ingestion points: The
analyzeReviewsfunction inSKILL.mdprocesses an array of user reviews. - Boundary markers: There are no boundary markers or instructions to the model to ignore potential instructions embedded within the reviews.
- Capability inventory: The skill uses an LLM (via the
CopyWriterclass) to generate copy and provides functions for writing output to the file system (exportToCSV,exportToJSON). - Sanitization: There is no evidence of sanitization or filtering of the review content before it is passed to the AI models for analysis and copy generation.
Audit Metadata