expansion-revenue-finder

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files, which creates a potential surface for indirect prompt injection where malicious instructions in those files could influence agent behavior. \n
  • Ingestion points: The skill searches for and reads various file formats including *.csv, *.json, *.md, *.txt, *.xlsx, and *.tsv as specified in references/data-inputs.md. \n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when processing the external data. \n
  • Capability inventory: The skill uses Read, Write, Bash, Grep, and Glob tools to analyze data and generate an expansion playbook. \n
  • Sanitization: The content of the data files is not sanitized or filtered before being used in the analysis and playbook generation. \n- [COMMAND_EXECUTION]: The skill employs Bash, Grep, and Glob to systematically search the user environment for keywords such as 'ARR', 'MRR', 'billing', and 'contract' to identify sensitive account information, as defined in SKILL.md and references/data-inputs.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — expansion-revenue-finder