promote
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
@every-env/spiral-clipackage from the npm registry. - [REMOTE_CODE_EXECUTION]: The skill executes vendor code via
npx @every-env/spiral-cli@latest setupto configure the integration. - [COMMAND_EXECUTION]: The skill extensively uses local CLI tools including
git,gh(GitHub CLI), and thespiralCLI to gather context, manage state, and generate content. - [DATA_EXFILTRATION]: Project summaries derived from local repo data are sent to the Spiral API to generate marketing drafts. This is the intended functionality of the tool.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data from pull requests and git logs.
- Ingestion points: Pull request content, commit messages, and changelog files.
- Boundary markers: No specific delimiters or safety instructions are used to isolate ingested data from the prompt logic.
- Capability inventory: Ingested data is used to generate prompts for the Spiral service and is displayed in the final output.
- Sanitization: The skill does not perform validation or sanitization of the data retrieved from external repository sources.
Audit Metadata