investor-update-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources such as CSV files, CRM exports, and product analytics reports. This creates a surface for indirect prompt injection where malicious instructions embedded in these files could influence the agent's behavior.
  • Ingestion points: SKILL.md (Step 7) describes parsing spreadsheets, CRM exports, and financial documents to extract KPIs and metrics.
  • Boundary markers: The instructions lack explicit boundary markers or instructions to disregard natural language directives found within the processed data, which may lead the agent to follow hidden instructions.
  • Capability inventory: The skill is restricted to file system tools (Read, Glob, Grep, Write, Edit) and does not have network access or shell execution capabilities, which significantly limits the potential impact of a successful injection.
  • Sanitization: No explicit sanitization or validation of the content of the data files is mentioned beyond extracting specific numerical values and trends.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:02 PM
Security Audit — agent-trust-hub — investor-update-writer