psp-onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content, specifically LinkedIn posts, podcast appearances, and job listings, to extract buyer vocabulary (Step 3: Vocabulary mining). This introduces a risk where malicious instructions could be embedded in the external data.
- Ingestion points: External content processed in Step 3 (SKILL.md) via user pasting or the WebFetch tool.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or provide the agent with "ignore embedded instructions" warnings for the ingested data.
- Capability inventory: The skill has access to Read, Write, and Grep tools, allowing it to modify files in the project root (brand-config.json and SOUL.md).
- Sanitization: Absent. There are no instructions for the agent to validate, filter, or escape the content extracted from external sources.
Audit Metadata