expansion-revenue-finder

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use the Bash tool to execute Grep and Glob operations on the filesystem to search for account data files.
  • [DATA_EXFILTRATION]: The skill is designed to systematically discover, read, and aggregate sensitive business information, including ARR, MRR, billing terms, and customer contact data. While it writes the output to a local file, the harvesting of this sensitive financial data represents an exposure risk.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through the ingestion of untrusted external data.
  • Ingestion points: Reads files in various formats including *.csv, *.json, *.md, *.txt, *.xlsx, and *.tsv from the working directory and user-specified paths.
  • Boundary markers: The instructions do not define any delimiters or provide warnings to ignore instructions embedded within the account data.
  • Capability inventory: The agent has access to Read, Write, and Bash tools, which are utilized during the processing of this untrusted data.
  • Sanitization: There is no mention of sanitization or validation of the ingested file contents before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 05:26 PM