01-content-calendar-global

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is a legitimate content planning tool. It does not perform network operations, access sensitive credentials, or attempt to modify the host system.
  • [NO_CODE]: The skill consists entirely of natural language instructions and templates. No scripts, binaries, or executable code snippets are included.
  • [PROMPT_INJECTION]: The skill reads external data from a local file, which is a potential surface for indirect prompt injection:
  • Ingestion points: Reads brand and regional data from .agents/product-marketing-context-global.md (referenced in SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are used to distinguish data from instructions in the ingested file.
  • Capability inventory: The skill has no dangerous capabilities, such as tool invocation, network access, or shell command execution.
  • Sanitization: No sanitization is performed on the content of the context file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 04:45 PM
Security Audit — agent-trust-hub — 01-content-calendar-global