skill-share
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill description specifies features for creating directory structures, generating files, and packaging skills into zip archives. This involves file system write access and execution of packaging utilities.
- [DATA_EXFILTRATION]: The skill uses the Rube integration to send skill metadata, summaries, and file links to external Slack channels. This represents an automated data transfer to an external service, which is the primary stated purpose of the skill.
- [PROMPT_INJECTION]: The skill creates new agent instructions based on untrusted user input, creating a surface for indirect prompt injection.
- Ingestion points: User-supplied skill name and description fields used to populate the SKILL.md template.
- Boundary markers: The description does not mention the use of delimiters or 'ignore embedded instructions' warnings in the generated output.
- Capability inventory: The skill has the ability to write to the file system (SKILL.md) and perform network operations (Slack messages).
- Sanitization: There is no documentation of input validation or escaping for the user-provided content before it is interpolated into the new skill's metadata.
Audit Metadata