NYC

knowledge-distribution

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill documentation specifies the use of Python 3.7+ scripts to automate the creation of skill directories and packaging processes. This involves local execution of scripts on the host system.
  • [DATA_EXFILTRATION] (LOW): The skill integrates with Slack via Rube to share skill metadata and summaries. While described as a notification feature, this mechanism could be misused to transmit sensitive file information or system metadata to external Slack workspaces.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted user input to generate executable skill structures.
  • Ingestion points: User-provided skill names and descriptions are used to populate SKILL.md and generate directory paths.
  • Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are documented for the input processing.
  • Capability inventory: Includes file system write access (directory/file creation), zip archiving, and network transmission (Slack API via Rube).
  • Sanitization: There is no evidence of sanitization or validation to prevent malicious instructions from being embedded in the generated skill metadata or used to manipulate file paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM