unit-economics

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion and processing of external SEC filings.
  • Ingestion points: The skill performs searches on SEC filings to extract management commentary and context in SKILL.md Step 4.
  • Boundary markers: The instructions do not define delimiters or protective instructions to isolate untrusted text from the agent's logic.
  • Capability inventory: The skill is capable of executing the infra/chart_generator.py script and writing HTML files to the reports/ directory.
  • Sanitization: The skill does not implement sanitization or validation for the data retrieved from external search results.
  • [COMMAND_EXECUTION]: The skill uses a local script, infra/chart_generator.py, to generate images for the unit economics report.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves financial series data from Daloopa and qualitative context from public SEC filings, which are established and well-known sources for investment research.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 07:47 PM
Security Audit — agent-trust-hub — unit-economics