content-sns-content
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and repurpose untrusted external data, such as YouTube lecture content or existing brand materials, as described in the repurposing workflow of
SKILL.md. It lacks specific instructions for boundary markers or sanitization to prevent the agent from executing instructions hidden within this data. - [COMMAND_EXECUTION]: The file
references/content-creator.mddefines the use of theBashtool for executing scripts. This capability, while functional, creates a risk where malicious instructions embedded in user data could attempt to execute unauthorized system commands. - [DYNAMIC_EXECUTION]: The skill instructions and supporting files (specifically
references/content-creator.md) describe a workflow that includes the usage of shell environments (Bash) to manage content or run scripts, representing a dynamic execution surface.
Audit Metadata