social-media-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (event details, tone, and campaign goals) which is then used to generate markdown files on the local file system. This introduces a vulnerability surface where a user could provide instructions that influence the agent's behavior or inject malicious content into the resulting files.\n
- Ingestion points: User-provided content gathered in Step 1 (Gather Information) of
SKILL.md.\n - Boundary markers: Absent. The skill instructions do not prescribe the use of delimiters or specific instructions to the agent to ignore embedded commands within the user data.\n
- Capability inventory: The skill uses the agent's capabilities to create directories and write markdown files in the
social-media/directory (Step 3 and 4 ofSKILL.md).\n - Sanitization: There are no instructions for sanitizing or validating user input before it is interpolated into templates and written to the file system.
Audit Metadata