sec-shenanigans-orchestrator

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process external SEC filings (10-K, 10-Q, 8-K) as described in SKILL.md. These files are attacker-controllable data sources.
  • Ingestion points: SEC filings are processed by the orchestration pipeline.
  • Boundary markers: Absent; no delimiters or instructions to ignore embedded content are specified to separate data from the model's instructions.
  • Capability inventory: The skill chains multiple high-level analysis tasks including evidence extraction and risk classification.
  • Sanitization: Absent; no validation or filtering of filing content is mentioned.
  • [No Code] (SAFE): This skill contains only orchestration instructions and documentation in Markdown and YAML formats. No executable scripts (Python, JavaScript, etc.) are included, which significantly reduces the direct execution risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 10:29 AM