ad-bidding-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the user and external web sources, creating a surface for injection attacks.
- Ingestion points: User-provided values during the 'Interview' phase in SKILL.md and live platform documentation fetched via the agent's browsing capabilities.
- Boundary markers: The instructions lack explicit delimiters or 'ignore embedded instructions' directives when processing external data.
- Capability inventory: No internal scripts are present; the skill relies on the agent's native text processing and browsing tools.
- Sanitization: No input validation or filtering is specified for the data collected from the user or external documentation.
- [NO_CODE]: The skill consists exclusively of markdown instructions, reference documentation, and test cases. It does not include any executable scripts, shell commands, or automated installers.
Audit Metadata