procore-security-basics
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, creating a surface for potential instructions to be embedded in data retrieved from the construction management platform.
- Ingestion points: Fetches company list from
api.procore.cominSKILL.md. - Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore or delimit instructions found within the API data.
- Capability inventory: The skill allows the use of
Bashfornpm,pip, andcurloperations as defined in the frontmatter ofSKILL.md. - Sanitization: Absent; the Python code snippet in
SKILL.mddirectly prints the results of the API call without validation or escaping.
Audit Metadata