skills/noelrohi/skills/handoff/Gen Agent Trust Hub

handoff

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests arbitrary conversation data and processes it to generate a summary. While this represents a vulnerability surface for indirect prompt injection, the risk is mitigated by the specific task (summarization) and the instruction to redact sensitive data.
  • Ingestion points: The current conversation history (SKILL.md).
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used for the input data.
  • Capability inventory: Writing files to the user's OS temporary directory (SKILL.md).
  • Sanitization: The skill explicitly instructs the agent to redact API keys, passwords, and personally identifiable information (PII) before saving the file (SKILL.md).
  • [DATA_EXPOSURE]: The skill directs output to the operating system's temporary directory. While temporary directories are generally user-specific, writing conversation summaries there constitutes a managed data flow rather than exfiltration. The inclusion of redaction guidelines for secrets demonstrates a security-aware design.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 04:59 PM
Security Audit — agent-trust-hub — handoff