people-enrichment

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files (CSV, XLSX, TXT) to perform lookups. This creates a potential surface for indirect prompt injection if the ingested data contains malicious instructions targeting the agent.
  • Ingestion points: The load_rows function in scripts/enrich.py reads data from files provided via the --input flag.
  • Boundary markers: Absent; the skill does not wrap processed content in delimiters or include instructions for the agent to ignore embedded commands within the data.
  • Capability inventory: The script performs outbound network requests to the People Data Labs API and possesses file write capabilities to generate Excel spreadsheets.
  • Sanitization: The script implements an _esc function in scripts/enrich.py that escapes single quotes in search parameters to prevent basic injection into the provider's SQL-like query interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 06:16 PM
Security Audit — agent-trust-hub — people-enrichment