lode-session-recap
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes raw conversation history to generate structured log entries.
- Ingestion points: The agent reads the full conversation history for the current session to extract decision context and technical changes (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore or delimit instructions found within the conversation data.
- Capability inventory: The skill possesses file-write capabilities through the execution of the
scripts/lode_raw.pyhelper script (scripts/lode_raw.py). - Sanitization: There is no evidence of sanitization or validation of the ingested conversation content before it is used to populate log entries.
- [COMMAND_EXECUTION]: The skill uses shell commands to execute a local Python script (
scripts/lode_raw.py) for resolving configuration paths and appending session data to JSON files. This is a core part of its intended logging functionality. - [EXTERNAL_DOWNLOADS]: The script
scripts/lode_raw.pyincludes an optional dependency on theyaml(PyYAML) package for parsing configuration files.
Audit Metadata