seo-audit
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external websites and internal project files which could contain malicious instructions.
- Ingestion points: The skill reads project-level context files such as .agents/marketing-strategy.md and .agents/marketing-learnings.md as specified in SKILL.md. It also fetches content from external URLs for auditing purposes using web_fetch and curl.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands were found in the skill's instructions.
- Capability inventory: The agent has the capability to perform network operations via web_fetch and curl tools.
- Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill instructions reference using curl and web_fetch to retrieve content from external websites for SEO analysis.
- Evidence: Mentions of web_fetch and curl are used to check crawlability, robots.txt, and indexation status in SKILL.md.
- Context: This behavior is aligned with the primary purpose of an SEO audit skill and targets user-specified websites.
Audit Metadata