multiplying-content-assets
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content, such as blog posts or podcast summaries, to generate new marketing assets. This creates an attack surface where malicious instructions hidden in the source material could potentially influence the agent's output or behavior.
- Ingestion points: SKILL.md (Discovery Question 4 and Example Prompts).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore commands within the source content.
- Capability inventory: The skill appears to be limited to text transformation and generation; no shell execution, file system modifications, or network capabilities are requested or used.
- Sanitization: No sanitization or validation of the input content is described.
- [NO_CODE]: The skill consists entirely of natural language instructions and metadata. It does not include any scripts, binaries, or automated shell commands, which significantly reduces the direct security risk profile of the skill.
Audit Metadata