content-calendar

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves data from the internet via WebSearch and WebFetch tools, which creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: Web research results used to build the content calendar in SKILL.md.
  • Boundary markers: Absent. The skill does not provide instructions to isolate or ignore potentially malicious commands within the external web data.
  • Capability inventory: The skill is configured with file manipulation tools including Write, Edit, Grep, and Glob in SKILL.md.
  • Sanitization: Absent. There are no content filtering or validation steps defined for the data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:39 PM