remove-technical-debt
Warn
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation of external packages from a third-party source. Evidence: The Operating Rules section in SKILL.md suggests providing the user with the command npx skills add wondelai/skills/slug --global.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external codebases and git logs without sufficient isolation. 1. Ingestion points: The agent reads the target codebase and git log output as specified in the Intake and Operating Rules sections of SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore instructions embedded in the analyzed code. 3. Capability inventory: The skill has the ability to write files to the project docs folder and execute shell commands. 4. Sanitization: No sanitization or validation of the ingested code content is performed.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform shell-based analysis of the project history. Evidence: Use of git log churn analysis in the Intake section and the recommendation of npx commands in the Operating Rules section.
Audit Metadata