standards-http

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data, including API specifications, database design files, and business flow descriptions, and incorporates this content into subagent prompts to generate documentation.
  • Ingestion points: Project files such as docs/product/business-flow.md, docs/specs/data/, and docs/specs/API/*.yaml are read in SKILL.md and the templates.
  • Boundary markers: The prompt templates in templates/ lack explicit delimiters or instructions to ignore embedded commands within the analyzed data files.
  • Capability inventory: The skill possesses file-writing capabilities, specifically creating docs/standards/http-handler-rule.md and updating the CLAUDE.md constraint file.
  • Sanitization: Content extracted from local files is interpolated into prompts without validation or sanitization, creating a surface where malicious instructions in project metadata or documentation could influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 02:49 PM
Security Audit — agent-trust-hub — standards-http