skills/bigdra50/skills/session-recap/Gen Agent Trust Hub

session-recap

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of a third-party Python package claude-session-index via pip. This tool is essential for the skill's primary functionality of indexing and searching session history.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from historical session logs which could potentially contain malicious instructions intended to influence the agent's behavior during the recap process.
  • Ingestion points: Past session content is retrieved and summarized using commands like sessions context <session_id> and sessions synthesize "<topic>" (referenced in SKILL.md).
  • Boundary markers: Absent. The instructions do not direct the agent to ignore or delimit embedded instructions within the session data being analyzed.
  • Capability inventory: The agent is granted access to the file system (Read, Grep), user interaction (AskUserQuestion), and a restricted Bash environment for the sessions CLI.
  • Sanitization: None. The skill instructs the agent to extract and reformat content from logs that include user-provided inputs and tool outputs without validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 08:54 PM
Security Audit — agent-trust-hub — session-recap