skillers-compact
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted conversation logs from multiple local sources which creates a surface for indirect prompt injection. Ingestion points: ~/.claude/projects/.jsonl, ~/.codex/sessions/.jsonl, and opencode.db. Boundary markers: The instructions require a mandatory redaction step using a local library. Capability inventory: Uses file system read/write and SQLite database queries. Sanitization: Implements a redact() function to filter sensitive content like API keys and tokens.
- [SAFE]: Reads session history and tool metadata. This access is required for the skill's stated purpose of compacting chat transcripts and no external data transmission was observed.
Audit Metadata