cs-onboard
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
git mv,cp -rf, andCopy-Itemto organize existing files and copy internal utility tools from the skill's package to the repository's.codestable/directory. These operations are essential for the skill's functionality and are performed locally within the project scope without privilege escalation. - [PROMPT_INJECTION]: The skill audits and processes existing markdown files within the repository to suggest migration paths, creating a surface for indirect prompt injection from potentially untrusted documentation in the codebase.
- Ingestion points: Scanning and reading all
.mdfiles in the repository during the initial auditing and migration steps. - Boundary markers: Absent; the instructions do not define delimiters to separate ingested file content from the agent's primary instructions.
- Capability inventory: The agent can read files, move files using
git mv, and copy directories usingcporCopy-Item. - Sanitization: Absent; the skill processes repository documentation without specific sanitization to prevent embedded instructions from influencing the agent.
Audit Metadata