superself
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
superself@0.6.1package from the npm registry. - [COMMAND_EXECUTION]: The skill makes extensive use of the
selfCLI to interact with project state, including commands likeself setup,self context,self work add, andself report. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves project context from an external repository, which could potentially contain malicious instructions embedded in the event log.
- Ingestion points: Project state is ingested via
self context,self work show, andself search(SKILL.md). - Boundary markers: No delimiters or explicit warnings to ignore embedded instructions are present.
- Capability inventory: The agent has the ability to execute shell commands through the
selfCLI (SKILL.md). - Sanitization: There is no mention of sanitization or validation for the content retrieved from the external state store.
Audit Metadata