working-capital
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of untrusted external data.
- Ingestion points: Data is ingested from
discover_companiesresults, various financial series, and management commentary from SEC filings (Step 4). - Boundary markers: No specific boundary markers or instructions to ignore embedded instructions within the ingested data are defined.
- Capability inventory: The skill has the capability to write files and generate HTML reports (
reports/{TICKER}_working_capital.html) and execute a local charting script (infra/chart_generator.py). - Sanitization: The skill does not explicitly instruct the agent to sanitize or escape external content before interpolating it into the final HTML report, which could allow malicious content within the financial records to affect the generated output.
Audit Metadata