report-generator

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the skill instructions.
  • [DATA_EXPOSURE]: The skill contains a security-positive instruction: "Reports name credential sources (.env keys), never values." This proactively prevents the accidental exposure of secrets in generated documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill is a consumer of data from external test artifacts (CSVs, markdown reports), which provides a surface for indirect prompt injection. Ingestion points: Local CSV and markdown artifact files (SKILL.md). Boundary markers: Absent; instructions do not specify using delimiters for the ingested content. Capability inventory: Limited to file reading and text synthesis; no network or command execution capabilities are available. Sanitization: Absent; the skill does not explicitly instruct the agent to sanitize artifact contents before inclusion.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 10:21 PM
Security Audit — agent-trust-hub — report-generator