read-x-links-local
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines tools that execute bash commands using
bunto process Twitter URLs locally. This is the primary intended function of the skill. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external X (Twitter) posts.
- Ingestion points: External content is fetched from X (Twitter) URLs provided as arguments to the tool.
- Boundary markers: No specific delimiters or instructions are provided in the skill files to help the agent distinguish between untrusted post content and its own instructions.
- Capability inventory: The skill has the ability to execute shell commands via the
Bashtool to run TypeScript files, providing a potential path for exploitation if the agent is manipulated by fetched content. - Sanitization: No sanitization of the fetched content is visible in the provided wrapper script or documentation.
Audit Metadata