ghm-template-sync
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell scripts found within the repository (e.g.,
.claude/hooks/*.sh) to verify they produce valid JSON. While this is a standard developer workflow for verification, it relies on the integrity of the code stored in the project environment. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the repository files and uses it to drive agent actions without validation.
- Ingestion points: Project files including
.claude/VERSION,CLAUDE.md, andsettings.json(found in SKILL.md). - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore malicious instructions that could be embedded in the repository content.
- Capability inventory: The skill utilizes the
Bashtool for local script execution andWrite/Edittools for modifying the filesystem (found in SKILL.md). - Sanitization: Absent. There are no instructions to sanitize, escape, or validate the data read from the repository before it is processed or used in shell commands.
Audit Metadata