thesis-tracker
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and parsing untrusted external data, including financial filings, earnings transcripts, and consensus expectations as described in Step 1 and Step 2.
- Ingestion points: External data sources such as tickers, filings, and earnings transcripts are parsed into pillar records and the evidence ledger.
- Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to separate external data from its own processing instructions.
- Capability inventory: The skill has the capability to write files to a task-specific directory and invoke other internal agent skills (e.g., catalyst-calendar, model-update) based on the findings from untrusted data.
- Sanitization: There is no mention of sanitizing or validating external content before it is interpolated into the agent's context and logic flow.
Audit Metadata