session-to-post
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands to collect project data and metrics. Evidence includes the use of git log, git diff, and find in modules/session-extraction.md, as well as triggering project-specific test runners like cargo test, pytest, and npm test.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from git history, file diffs, and conversation logs which could contain malicious instructions.
- Ingestion points: Git logs, file inventory, and conversation history are read in modules/session-extraction.md and the main methodology.
- Boundary markers: No explicit delimiters or instructions are used to isolate ingested data from the generation instructions.
- Capability inventory: The skill can execute shell commands and write files to the local filesystem.
- Sanitization: Ingested text is not sanitized before being used for content generation.
Audit Metadata