kotlinx-serialization
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs static analysis on user-provided Kotlin project files to provide configuration advice. While this introduces a potential surface for indirect prompt injection via malicious source code, the risk is mitigated by the tool's design.
- Ingestion points: The
scripts/inspect-project.pyscript reads.kt,.gradle,.toml, and.xmlfiles from the project directory provided to the--rootargument. - Boundary markers: The instructions in
SKILL.mdadvise the agent to treat findings as candidates and manually inspect the enclosing context before making claims. - Capability inventory: The skill provides architectural advice, dependency checks, and configuration troubleshooting; it does not perform automated code modification or network operations based on the analyzed code.
- Sanitization: The helper script uses structured parsing (via
tomllibandxml.etree.ElementTree) and specific regex patterns rather than executing the code, limiting the impact of malicious content embedded in the project files.
Audit Metadata