export-session-as-markdown
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script to process transcripts.
- Evidence: Steps 3 in
SKILL.mdrunspython3 "${CLAUDE_PLUGIN_ROOT}/scripts/reduce-transcript.py" "<transcript_path>" "<output_path>" --markdown. - Context: The script is part of the
ed3d-session-reflectionplugin, which is a resource associated with the vendor. - [PROMPT_INJECTION]: The skill processes session transcripts, which constitutes an indirect prompt injection surface.
- Ingestion points: Reads conversation history from
.jsonlfiles (mentioned inSKILL.mdsteps). - Boundary markers: None specified in the instructions for the data processing step.
- Capability inventory: Executes a Python subprocess to write files to the local system (Step 3 in
SKILL.md). - Sanitization: The skill does not explicitly mention sanitizing the transcript content before conversion.
Audit Metadata