blog-calendar

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate content planning by scanning the local directory for blog posts to understand context and identify content decay.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for data processed at runtime. Ingestion points: Scans for *.md, *.mdx, and *.html files in the repository (SKILL.md, Step 1). Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded content within the analyzed files. Capability inventory: Uses globbing and file reading for discovery, file writing for calendar generation, and web search for trend validation. Sanitization: There is no mention of sanitizing or filtering the blog content before it is used for planning.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 04:57 AM
Security Audit — agent-trust-hub — blog-calendar