erne-learn
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers the execution of local Node.js scripts (
extract-session-patterns.jsandvalidate-content.js) using thenodecommand to analyze session data and manage generated content. - [PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by design.
- Ingestion points: The
extract-session-patterns.jsscript scans recent tool calls and file changes to identify reusable patterns (SKILL.md). - Boundary markers: No explicit delimiters or boundary markers are described to prevent the extraction script from interpreting malicious instructions within the session data as valid patterns.
- Capability inventory: The skill has the capability to execute shell commands (
node) and perform filesystem writes to the.claude/rules/and.claude/skills/directories (SKILL.md). - Sanitization: The skill includes a validation step (
validate-content.js), but this appears limited to checking frontmatter and file conflicts rather than sanitizing patterns for adversarial content.
Audit Metadata