seo-keyword-difficulty
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its instructions to fetch and analyze content from arbitrary third-party websites. In Phase 1, Step 2, the agent is directed to use
WebFetchto process metadata and body text from top organic search results. Maliciously crafted content on these pages could be used to influence the agent's analysis or hijack the session.\n - Ingestion points: Untrusted data enters the agent context via
WebFetchcalls to competitor URLs inSKILL.md(Phase 1, Step 2).\n - Boundary markers: None. The instructions lack explicit delimiters or 'ignore' directives to prevent the agent from obeying instructions embedded in the external data.\n
- Capability inventory: The skill uses
WebFetch,WebSearch, and makes calls to theseo-web-cafeandgoogle-search-consoleMCP tools.\n - Sanitization: None. The agent is instructed to process external content directly without any validation or escaping mechanisms.
Audit Metadata