kata-resume-work

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill utilizes hardcoded shell commands to manage internal state and verify file existence. Evidence: references/resume-project.md contains bash scripts using ls, cat, and find to check the .planning/ directory. These operations are limited to a specific local path, which restricts the potential for arbitrary command execution.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection by design. Ingestion points: It reads content from STATE.md, PROJECT.md, and .continue-here*.md files within the references/resume-project.md workflow. Boundary markers: Analysis shows no delimiters or specific 'ignore embedded instructions' warnings are applied to the data read from these files. Capability inventory: The skill has the ability to execute shell commands, write to the filesystem (STATE.md), and route the user to further workflows. Sanitization: No sanitization or validation of the ingested file content is performed before the data is presented to the agent or used to determine next actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 08:19 PM