bid-strategy-planner
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could contain malicious instructions.
- Ingestion points: SKILL.md and references/skill-contract.md specify reading user-provided context, project files, scraped web pages, reviews, and public data sources.
- Boundary markers: Present. Both SKILL.md and references/skill-contract.md explicitly instruct the agent to treat such inputs as untrusted evidence and to disregard instructions embedded within the data.
- Capability inventory: references/connectors.md identifies potential interactions with advertising platforms (Google Ads, Meta Ads) and RevOps tools (HubSpot, Salesforce). However, the skill contract requires explicit user authorization for any persistent writes, account mutations, or external side effects.
- Sanitization: The instructions mandate that the agent label evidence by its source and certainty level and verify time-sensitive platform rules before acting.
Audit Metadata