distributing-omnichannel-content
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and process arbitrary external content such as blog posts, transcripts, or data from URLs. This creates a potential surface for indirect prompt injection where malicious instructions embedded in the source material could influence the agent's behavior during content generation.
- Ingestion points: Source content provided by the user (Discovery Question #4) or retrieved from a user-provided URL.
- Boundary markers: Absent; there are no explicit instructions for the agent to treat input as data-only or to ignore embedded instructions.
- Capability inventory: The agent is instructed to generate text for various platforms and organize outputs into a local folder structure.
- Sanitization: Absent; the skill does not specify any validation or cleaning of the input text.
- [No Code] (SAFE): The skill consists entirely of markdown-based instructions and YAML metadata. It does not ship with or reference any Python scripts, Node.js packages, binary executables, or shell commands, which eliminates the risk of direct remote code execution or privilege escalation via the skill's own assets.
Audit Metadata