social-content-creation
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process external, untrusted content, which creates a standard surface for indirect prompt injection attacks.\n
- Ingestion points: In
SKILL.md(Phase 1), the agent is instructed to read full newsletters, articles, or podcast transcripts as source material to identify concepts.\n - Boundary markers: The workflow lacks instructions for the agent to use delimiters (like XML tags or triple quotes) or explicit commands to ignore instructions that might be embedded in the source material.\n
- Capability inventory: The skill instructs the agent to write several output files to the local environment (e.g.,
[Source]_Social_Posts.mdand[Source]_Framework_Matches.md), meaning malicious content in the source could potentially influence file creation or content formatting.\n - Sanitization: There are no validation or sanitization steps defined for the external content before it is processed or written to the output files.
Audit Metadata