swot-analysis
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather data from external sources, which could potentially contain adversarial instructions meant to influence the analysis.
- Ingestion points: The skill specifies gathering data from 'docs, metrics, customer feedback, competitor pages and the codebase' in the 'Before you start' section of SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external data as untrusted or to ignore instructions embedded within those sources.
- Capability inventory: The skill definition does not list any dangerous tools (like shell execution, file writing, or network requests) that could be abused by an injection; it primarily focuses on generating a text-based analysis table.
- Sanitization: No sanitization or validation logic is defined for the input data.
Audit Metadata