content-pipeline

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied topics and local file contents as inputs for sequential subagents (research-analyst, editor-in-chief, social-amplifier). Maliciously crafted content within these inputs could potentially influence the behavior of the subagents.
  • Ingestion points: The skill accepts a [topic or file path] as input for the orchestration pipeline in SKILL.md.
  • Boundary markers: No explicit delimiters (like XML tags or triple quotes) or 'ignore embedded instructions' warnings are defined in the agent spawning instructions in REFERENCE.md.
  • Capability inventory: The skill has the capability to spawn new agents and write output files to the local file system (e.g., ./research-briefs/, ./content/).
  • Sanitization: There is no evidence of content sanitization, validation, or filtering applied to the external input before it is interpolated into the prompts for the subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — content-pipeline