edgespeak-align
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media files and transcript text, which constitutes an ingestion surface for untrusted data.
- Ingestion points: Media file paths and transcript text (passed via string or file) are used as inputs for the
edgespeak-cli aligncommand inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the provided transcript text.
- Capability inventory: The skill utilizes subprocess execution for the
edgespeak-cliand supports file system writes using the-ooutput flag. - Sanitization: No sanitization or validation of the transcript content is described in the skill instructions.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes a link to the official vendor documentation for CLI installation at
https://edgespeak.com/docs/cli#install. The instructions explicitly state that the user should execute the installation command rather than the agent doing so automatically.
Audit Metadata