seo-strategy
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of performing live external research and reading untrusted websites.\n
- Ingestion points: The agent retrieves data from external URLs during its "Discover", "Validate", and "Compare" branches, and reads existing repository files like
SEO.mdand content inseo-reports/as outlined inSKILL.mdandreferences/research-method.md.\n - Boundary markers: There are no specific instructions or delimiters used to separate the content of external websites from the agent's internal reasoning or output generation process in the provided instruction files.\n
- Capability inventory: The skill allows the agent to write and maintain several files in the repository, including
SEO-STRATEGY.md, proposals, and history snapshots, as defined inreferences/templates.md.\n - Sanitization: The instructions do not include any guidance for sanitizing or filtering external content before it is used to form a thesis or roadmap.
Audit Metadata