Ad Creative Strategist
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by combining the ingestion of untrusted external data with high-privilege tools. External content could potentially contain instructions that manipulate the agent's behavior.\n
- Ingestion points: The skill utilizes
WebFetchandWebSearchtools inSKILL.mdto retrieve and analyze external competitive ad copy and performance data.\n - Boundary markers: There are no explicit instructions or delimiters defined to separate untrusted external content from the agent's core instructions, increasing the risk of the agent following embedded commands.\n
- Capability inventory: The skill has access to
Bash,Write, andEdittools, providing a path for an attacker to execute commands or modify local files if an injection is successful.\n - Sanitization: No mechanisms for sanitizing, validating, or filtering the content retrieved from the web are mentioned in the skill instructions.
Audit Metadata