session-analyst
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script at
~/.claude/evolution/bin/evolve-collect.shto update internal data candidates based on recent logs. This is a routine internal maintenance operation. - [PROMPT_INJECTION]: The skill processes untrusted data from historical session records, posing a theoretical indirect prompt injection surface.
- Ingestion points: Reads historical interaction data from
~/.claude/evolution/records/*.jsonl. - Boundary markers: No explicit delimiters or instruction-bypass warnings are defined for the record scanning logic.
- Capability inventory: The skill can execute shell commands via bash and write reports to the local file system.
- Sanitization: The protocol does not specify sanitization or validation of the text content within the records before processing.
Audit Metadata