blog-calendar

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection via processed data.
  • Ingestion points: The agent is instructed to scan existing blog posts (using Glob for *.md, *.mdx, and *.html files) to gather context and perform content decay detection.
  • Boundary markers: The workflow does not define any delimiters or system instructions to ignore embedded prompts within the blog content it reads.
  • Capability inventory: The skill is granted powerful capabilities including Bash, Write, WebFetch, and WebSearch permissions.
  • Sanitization: There are no sanitization, escaping, or validation steps described for the data ingested from the file system before it influences agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 11:10 PM