event-format-selection

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and consists of markdown files (SKILL.md and reference documents). It contains no scripts, binaries, or automated shell commands that would impact the host system or process sensitive data.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow based on a user interview, creating a surface for ingesting external data.
  • Ingestion points: User input provided in response to the questions in the "Interview" section of SKILL.md.
  • Boundary markers: Absent; the instructions do not implement specific delimiters for untrusted input.
  • Capability inventory: The skill possesses no capabilities beyond text analysis and recommendation. There are no tools for network exfiltration, file system modification, or command execution included in the skill definition.
  • Sanitization: None observed.
  • Assessment: Because the skill operates in a restricted text-only context without access to dangerous system or network tools, the risk of indirect prompt injection is considered negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:13 PM
Security Audit — agent-trust-hub — event-format-selection