thank-you-note

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration attempts were detected in the skill instructions.
  • [COMMAND_EXECUTION]: The skill configuration in SKILL.md includes the Bash tool in the allowed-tools list. While this grants the agent shell access, no shell commands are explicitly invoked in the skill's logic.
  • [PROMPT_INJECTION]: The skill retrieves context from local YAML files to personalize notes, which constitutes a surface for indirect prompt injection if those files contain untrusted content.
  • Ingestion points: SKILL.md (Step 1: Load Context reads interview-history.yaml, intel/{company-slug}.yaml, and career-plan.yaml)
  • Boundary markers: Absent; context data is interpolated directly into the generation prompt.
  • Capability inventory: Bash, Write, Edit, mcp__blackboard-channel__write_to_blackboard
  • Sanitization: Absent; no validation or escaping of external content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 05:36 AM
Security Audit — agent-trust-hub — thank-you-note