financial-snapshot-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from financial filings and earnings releases to create local reports.\n
  • Ingestion points: The skill workflow involves loading filings, earnings releases, and market data as specified in SKILL.md.\n
  • Boundary markers: The instructions do not specify delimiters or protective prompts to isolate external data from the agent's core instructions.\n
  • Capability inventory: The skill has the capability to write and archive files in specific project directories (research/targets/target/evidence/) as defined in SKILL.md.\n
  • Sanitization: There are no requirements for sanitizing or validating data extracted from these external sources before processing or writing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 10:23 PM
Security Audit — agent-trust-hub — financial-snapshot-analysis