session-to-post

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard system and development commands including git, find, wc, and package-specific test runners (cargo, npm, pytest) to gather session metrics and history. These operations are limited to data extraction for documentation purposes.
  • [PROMPT_INJECTION]: The skill processes data from the local environment (such as git commit messages and file contents) to generate content, which presents an indirect prompt injection surface.
  • Ingestion points: modules/session-extraction.md (extracts git history and file content).
  • Boundary markers: Absent; the templates in modules/narrative-structure.md do not include specific delimiters to isolate external content from instructions.
  • Capability inventory: The skill is configured with Bash and Write capabilities in SKILL.md.
  • Sanitization: No explicit sanitization or filtering of the extracted session data is performed before it is used in prompt templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:26 PM
Security Audit — agent-trust-hub — session-to-post