skills/wshobson/agents/superself/Gen Agent Trust Hub

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@0.6.1 package from the npm registry.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the self CLI to interact with project state, including commands like self setup, self context, self work add, and self 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, and self 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 self CLI (SKILL.md).
  • Sanitization: There is no mention of sanitization or validation for the content retrieved from the external state store.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 09:18 PM
Security Audit — agent-trust-hub — superself