ad-copy-writer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain instructions designed to manipulate the agent.
- Ingestion points: The skill uses
WebFetchto extract content from user-provided URLs andWebSearchto retrieve competitor information as described in the research steps of SKILL.md. - Boundary markers: No specific delimiters or "ignore instructions" directives are provided to the agent to separate fetched data from its core logic.
- Capability inventory: The skill is granted permissions for
Bash,Write,WebFetch, andWebSearchin the allowed-tools configuration. - Sanitization: No sanitization, validation, or filtering logic is defined for the content retrieved from external websites before it is processed.
Audit Metadata