seven-powers
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external "source material" and "claims" provided by the user to diagnose business power mechanisms. This creates a surface for indirect prompt injection if the analyzed text contains instructions designed to manipulate the agent's output.
- Ingestion points: Business memos, product strategy documents, and candidate power claims processed during the 'Workflow' section in SKILL.md.
- Boundary markers: The skill does not include specific delimiters or warnings to ignore instructions embedded within the analyzed business data.
- Capability inventory: The skill is restricted to 'Read' and 'Grep' tools (frontmatter). It does not have network access, file-write capabilities, or shell execution permissions.
- Sanitization: No explicit sanitization or validation of the input source material is performed.
Audit Metadata