cowork-home-inventory

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources.
  • Ingestion points: The skill reads files from user-provided folders, including PDF receipts, email exports, and images (SKILL.md).
  • Boundary markers: There are no instructions to use delimiters or to disregard potential instructions found within the processed files.
  • Capability inventory: The skill utilizes tools such as "Bash", "Write", "Read", and "WebSearch" (SKILL.md frontmatter).
  • Sanitization: The instructions do not specify any validation or sanitization steps for the text extracted from receipts or emails.
  • [COMMAND_EXECUTION]: The skill's configuration allows access to the "Bash" tool (SKILL.md frontmatter). While not inherently malicious, this tool provides a high-privilege execution environment that could be targeted if an indirect prompt injection occurs through malicious text embedded in a receipt or email.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 01:14 PM
Security Audit — agent-trust-hub — cowork-home-inventory