ecc-tools-cost-audit
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and analysis of external data from the
ECC-Toolsrepository, which introduces a surface for instructions embedded in data to influence the agent. - Ingestion points: Webhook routers, queue producers, queue consumers, and pull request metadata in the target repository (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing data from the repo's entry points or queues.
- Capability inventory: The agent is authorized to switch repositories, check local diffs, modify code (PR/branch helpers), and potentially perform deployment actions (SKILL.md).
- Sanitization: No explicit sanitization or validation steps are defined for data retrieved from webhook events or queue workers before the agent processes it.
Audit Metadata