gap-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external websites (via WebFetch and WebSearch) and SDK documentation (via the context7 MCP server) to generate a gap analysis report. Malicious content on third-party documentation pages or manipulated search results could attempt to influence the agent's summary or the report generation process.
- Ingestion points: WebFetch/WebSearch results are used in the auditing workflow (SKILL.md, Step 3 & 4).
- Boundary markers: There are no explicit instructions to use delimiters or ignore potential commands embedded within the external documentation content during processing.
- Capability inventory: The skill possesses the ability to write files to the
.agent/gap-analysis/directory, dispatch subagents (Explore), and perform network operations. - Sanitization: The instructions do not specify sanitization or escaping of the fetched external content before it is interpolated into the final report template.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from several well-known service providers to perform its audit, including OpenAI, Anthropic, Google Gemini, Ollama, Groq, xAI (Grok), OpenRouter, Amazon Bedrock, Fal.ai, ElevenLabs, and BytePlus. These references target official documentation and API references.
Audit Metadata