claude-code-transcripts

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the claude-code-transcripts CLI tool and gh CLI to automate the conversion and publishing of session logs.
  • [EXTERNAL_DOWNLOADS]: Instructions include installing the claude-code-transcripts package from PyPI using standard package managers like uv or pip.
  • [DATA_EXFILTRATION]: Facilitates the transfer of local session data from ~/.claude/projects to GitHub Gists or local directories. It also allows fetching session data from external URLs.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by processing external or local session data which may contain embedded instructions.
  • Ingestion points: Reads session data from ~/.claude/projects/*/session.jsonl and user-provided URLs.
  • Boundary markers: Not explicitly defined in the provided instructions to isolate the agent from instructions within the transcripts.
  • Capability inventory: Includes shell command execution, file system access to session logs, and network operations to GitHub and the Claude API.
  • Sanitization: While the tool provides HTML formatting and syntax highlighting, it does not explicitly describe measures to sanitize malicious prompts embedded in the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 06:51 PM
Security Audit — agent-trust-hub — claude-code-transcripts