session-compress

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted conversation history to generate summaries, creating a surface for indirect prompt injection. Malicious instructions in the chat history could potentially influence the agent's summarization logic or future actions when the context is reloaded.\n
  • Ingestion points: The skill scans the entire session history from start to the current message (SKILL.md).\n
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic.\n
  • Capability inventory: The skill can execute shell commands (mkdir) and write files to the local filesystem (SKILL.md).\n
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the session content before it is processed or written to disk.\n- [COMMAND_EXECUTION]: The skill uses shell commands (mkdir -p ~/.claude/sessions/compressed) to ensure the existence of its storage directory. While this is a standard administrative task for the skill's functionality, it involves direct interaction with the system shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:34 AM
Security Audit — agent-trust-hub — session-compress