skills/benjaroy/riff/critique/Gen Agent Trust Hub

critique

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because its primary purpose is to ingest and analyze untrusted, user-provided text (essays). A malicious essay could attempt to override agent instructions or influence the output format.
  • Ingestion points: User-provided essays processed via the primary critique function.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested essay.
  • Capability inventory: The skill is limited to text analysis and generation; it does not request network access, file system writes, or shell execution.
  • Sanitization: No explicit sanitization or filtering of the user-provided input is performed.
  • [SAFE]: Analysis of the skill instructions and metadata revealed no evidence of data exfiltration, hardcoded credentials, or persistence mechanisms. The reference to a local 'base.md' file is a standard practice for shared configuration in modular agent skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 05:51 PM