suede-programmatic-seo
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill framework involves ingesting external data (identified as scraped, public, or licensed data in the 'Data Requirements' section of SKILL.md) to generate SEO templates. This creates a potential surface for indirect prompt injection if the source data contains adversarial instructions intended to subvert agent logic.\n
- Ingestion points: External data sources defined in SKILL.md.\n
- Boundary markers: None specified to isolate external data from the agent's generation instructions.\n
- Capability inventory: The agent is instructed to write literal templates and structured markdown based on the provided data (SKILL.md
- Output Contract).\n
- Sanitization: No explicit sanitization, escaping, or validation of the external content is required by the instructions.
Audit Metadata