docs-audit
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external competitor websites during the competitive comparison phase.\n
- Ingestion points: The skill fetches content from 1–3 relevant comparator pages via web access in Step 5 (SKILL.md).\n
- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts in the fetched external content are present.\n
- Capability inventory: The skill is designed to produce a structured markdown report. It does not contain capabilities for subprocess execution, file system modifications, or exfiltration of local environment data.\n
- Sanitization: There is no evidence of sanitization or validation of the fetched HTML/Markdown content before it is incorporated into the agent's context.\n- [EXTERNAL_DOWNLOADS]: The skill retrieves content from external network locations to perform audits.\n
- Fetches the published version of documentation from the vendor-associated domain strandsagents.com.\n
- Fetches arbitrary documentation pages from competitor websites as directed by the user or identified during search.
Audit Metadata