seo-content-brief
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data (topic, keyword, audience) which could be used as a vector for indirect prompt injection.
- Ingestion points: Arguments defined in
SKILL.mdincludingtopic,keyword,audience, andconversion goalare derived from user input. - Boundary markers: The skill does not define explicit delimiters or specific instructions for the agent to ignore potentially malicious embedded commands within these input fields.
- Capability inventory: The skill configuration in
SKILL.mdallows for the use ofReadandWritetools, providing a surface where injected instructions could attempt to interact with the file system. - Sanitization: No input validation or sanitization mechanisms are present in the skill instructions or referenced markdown files to filter content provided in the arguments.
Audit Metadata