seo-content-writer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The 'Skill Boundaries' section incorrectly describes constraints related to 'audio production' and 'audio engineering,' which are irrelevant to the skill's primary function of SEO content writing. This is likely a result of an incomplete template update.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it is designed to ingest and audit untrusted data from external sources or user inputs.
- Ingestion points: The skill accepts user-provided text for optimization, auditing, and brief creation as outlined in the 'How to Use' section of SKILL.md.
- Boundary markers: The instructions lack explicit delimiters (like XML tags or triple quotes) or specific instructions for the agent to ignore command-like text embedded within the analyzed content.
- Capability inventory: The skill is restricted to text generation and does not have access to tools for network operations, shell execution, or file system modifications.
- Sanitization: There is no evidence of input validation or sanitization logic to mitigate instructions hidden in the data being processed.
Audit Metadata