paid-ads-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is instructed to read local configuration files to gather project-specific details, creating a surface where content from these files enters the agent's context.
- Ingestion points: The skill reads
.agents/project-context.mdor.claude/project-context.mdas specified inSKILL.mdbefore proceeding with the advisory tasks. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested context files.
- Capability inventory: The skill's functionality is limited to generating text-based marketing strategy and referencing other platform-specific skills; it does not contain code for shell execution, network exfiltration, or unauthorized file system writes.
- Sanitization: No sanitization or validation of the external context content is performed before interpolation into the prompt.
Audit Metadata