skills/hashintel/labs/shaping-kickoff/Gen Agent Trust Hub

shaping-kickoff

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and metadata do not contain any malicious patterns or security risks. The skill focuses on text transformation and organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external text files (kickoff transcripts) provided by the user. While this ingestion represents a surface for indirect prompt injection, the skill does not define or utilize dangerous capabilities such as network operations or system modifications, which significantly limits the potential impact.
  • Ingestion points: Kickoff transcript files (SKILL.md argument-hint).
  • Boundary markers: None provided in the instructions to delimit external content.
  • Capability inventory: The skill specifies text output generation only; no scripts or tools for file writing, network access, or command execution are included.
  • Sanitization: No explicit sanitization or validation of the input transcript content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:31 AM
Security Audit — agent-trust-hub — shaping-kickoff