procore-cost-tuning

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to ingest and process data from the Procore construction management platform, which introduces a surface for indirect prompt injection if the retrieved project data contains instructions meant to override agent behavior.
  • Ingestion points: Data is fetched from the Procore API companies endpoint (https://api.procore.com/rest/v1.0/companies) in the code snippet within SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard natural language commands found within the API responses.
  • Capability inventory: The skill is configured with access to the Bash tool (restricted to npm, pip, and curl), which could potentially be used if a successful injection occurred.
  • Sanitization: The implementation patterns do not include sanitization or validation logic for the data returned from external API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:56 AM
Security Audit — agent-trust-hub — procore-cost-tuning