google-ads-anomaly-detection
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external file named .agents/product-marketing-context.md to gather information before beginning diagnostics. This creates a potential surface for indirect prompt injection if the ingested file contains adversarial instructions. 1. Ingestion points: .agents/product-marketing-context.md referenced in the 'Before Starting' section. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this external content as untrusted. 3. Capability inventory: The skill is purely instructional and does not define tools, scripts, or network capabilities within its own code. 4. Sanitization: No sanitization or validation logic is present for the ingested content.
- [NO_CODE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or system-level commands, which significantly reduces its potential security impact.
Audit Metadata