verify-contact-book

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from a contact book database and interpolates it into a generated Markdown report. This creates a surface for indirect prompt injection where malicious content within the source data could influence the agent or other downstream systems when the report is processed.
  • Ingestion points: SQL database tables including organization, person, field_status, and signal (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content within the processed data.
  • Capability inventory: The skill has the capability to execute SQL queries and write files to the local filesystem.
  • Sanitization: No explicit sanitization or validation of the data retrieved from the database is described before it is written to the report.
  • [COMMAND_EXECUTION]: The skill generates a file path using a variable (leads/<slug>/COVERAGE.md). If the <slug> is derived from untrusted input without validation, it could potentially be exploited for path traversal, allowing the agent to write files to unintended locations on the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 04:26 PM
Security Audit — agent-trust-hub — verify-contact-book