template-usage

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill behaves as described, utilizing official Harness MCP tools for auditing template adoption. No malicious patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes template definitions and usage data retrieved from the Harness environment.
  • Ingestion points: Data is fetched via harness_search and harness_get tools as described in SKILL.md.
  • Boundary markers: None explicitly defined in instructions, but data is structured into predefined report templates.
  • Capability inventory: Limited to read-only metadata retrieval and report formatting; no tools for code execution, filesystem writing, or external network access are authorized.
  • Sanitization: Standard API parsing by the Harness MCP server; the skill focuses on reporting existing metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:25 PM
Security Audit — agent-trust-hub — template-usage