kotlin-multiplatform-skill-harvester
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a bundled Python script
scripts/harvest_lessons.pyto process local project files and generate reports. - [COMMAND_EXECUTION]: Uses the GitHub CLI (
gh) to interact with issues on the author's repository (ronjunevaldoz/kmm-agent-skills) for fetching consumer feedback. - [EXTERNAL_DOWNLOADS]: Retrieves external data from GitHub issues via the
ghcommand-line tool. - [PROMPT_INJECTION]: Processes untrusted consumer-provided content from
docs/lessons/*.mdfiles, which acts as an indirect prompt injection surface. - Ingestion points: Files located in
docs/lessons/*.mdacross various consumer projects. - Boundary markers: Content is parsed based on markdown headings and YAML frontmatter structure.
- Capability inventory: Execution of
ghCLI commands and file system modifications (applying diffs to other skills). - Sanitization: The skill explicitly requires a manual review phase (Step 5) and user confirmation before any modifications are committed to the file system.
Audit Metadata