skills/iwanhe/pandawa/cold-email/Gen Agent Trust Hub

cold-email

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external email drafts and performance data, creating a surface for potential indirect prompt injection.
  • Ingestion points: The scripts/email_sequence_analyzer.py script accepts JSON-formatted email content via standard input or file paths for quality analysis. SKILL.md also instructs the agent to process existing email drafts provided by the user.
  • Boundary markers: The instructions do not currently include explicit boundary markers or directives for the agent to ignore instructions embedded within the analyzed email text.
  • Capability inventory: The skill's capabilities are strictly limited to text analysis, scoring, and providing recommendations. The included Python script does not have network access, file system write permissions, or the ability to execute shell commands.
  • Sanitization: While the script uses regular expressions to detect patterns (like spam triggers and CTAs), it does not explicitly sanitize the text to prevent the AI from following embedded instructions; however, the lack of dangerous capabilities mitigates this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:32 PM
Security Audit — agent-trust-hub — cold-email