skill-forge-publish
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (mkdir, cp) and local Python scripts (scripts/package_skill.py) to facilitate the packaging and distribution process.
- [DYNAMIC_EXECUTION]: The agent is tasked with generating an install.sh script. Generating executable shell scripts based on user-provided project structures is a dynamic execution pattern.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from a user-specified directory during validation and packaging steps.
- Ingestion points: Files located at the user-provided (SKILL.md).
- Boundary markers: Absent; there are no instructions to isolate or treat ingested file content as untrusted data.
- Capability inventory: The skill has access to file system writes, directory creation, and local script execution.
- Sanitization: Absent; the instructions do not specify validation or sanitization of external content before processing or inclusion in generated scripts.
Audit Metadata