twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external data sources.
- Ingestion points: The skill utilizes
infsh/agent-browserto visit URLs andtavily/search-assistantto perform web searches for content generation (as seen in SKILL.md). - Boundary markers: No delimiters or instructions to ignore embedded instructions are provided when incorporating retrieved data into the thread creation process.
- Capability inventory: The agent has the capability to post content to social media (
x/post-create), generate images from HTML, and run shell commands viainfsh. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external sources before it is processed.
- [COMMAND_EXECUTION]: The skill relies on the
infshcommand-line tool for all primary operations. - Evidence: Examples in the skill demonstrate the use of
infsh login,infsh app run x/post-create, andinfsh app run infsh/agent-browser. This is consistent with the skill's purpose as an extension of the inference.sh platform.
Audit Metadata