directory-submission
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: This skill presents an indirect prompt injection surface as it processes potentially untrusted data from local files and the internet.
- Ingestion points: The agent is instructed to read
.claude/product-marketing-context.mdand.cursor/product-marketing-context.md, and to 'search the web' for missing product information. - Boundary markers: The prompt does not specify the use of delimiters or 'ignore instructions' warnings when processing these external data sources.
- Capability inventory: The skill uses the gathered data to create ready-to-paste submission content, including descriptions and taglines.
- Sanitization: There are no instructions for the agent to sanitize, escape, or validate the content retrieved from external sources.
Audit Metadata