report-generation

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources (JSON, CSV, YAML, and API responses) to generate narrative insights. This creates a surface for indirect prompt injection where malicious instructions embedded in the data could influence the agent's behavior. Ingestion points: External file and API payloads (SKILL.md, Workflow Step 1). Boundary markers: None explicitly defined in the instructions to isolate data from commands. Capability inventory: Data ingestion, metric calculation, and report rendering in multiple formats. Sanitization: Not specified beyond basic schema and data type validation.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and usage examples; no executable scripts, configurations, or binary files are provided.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:01 PM
Security Audit — agent-trust-hub — report-generation