fetch-issue
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill uses
bunxto download and execute the latest version of the@willbooster/agent-skillspackage from the NPM registry at runtime. - [COMMAND_EXECUTION]: The skill executes shell commands using the
bunandghtools to fetch repository and issue data. - [EXTERNAL_DOWNLOADS]: Fetches the tool's logic from the public NPM registry during execution.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting untrusted data from external sources.
- Ingestion points: GitHub issue bodies and comments (SKILL.md).
- Boundary markers: Absent. The skill does not define delimiters to separate fetched content from agent instructions.
- Capability inventory: The agent has access to shell execution tools (bun, gh) when processing the retrieved issue content.
- Sanitization: Absent. No filtering or validation of the external content is described before it enters the agent's context.
Audit Metadata