tech-debt-audit
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and analyzing the entire codebase of the repository it is auditing, which constitutes untrusted input. Maliciously crafted code or comments within the target repository could attempt to influence the agent's behavior during the audit.
- Ingestion points: Phase 1 instructions require reading the README, package manifests (package.json, pyproject.toml, etc.), architecture documentation, and git log. Phase 2 involves scanning all source files using rg and ast-grep.
- Boundary markers: No explicit delimiters or instructions are used to separate untrusted codebase content from the agent's internal reasoning or to warn the agent against following instructions found in the data.
- Capability inventory: The skill uses file system access (read/write), shell command execution (git, linters, audit tools), and the ability to spawn subagents via the Task tool.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the repository content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The installation section of the project documentation suggests fetching the skill via curl from a third-party GitHub repository (github.com/ksimback/tech-debt-skill). This encourages the installation of unverified code from a source outside the author's apparent domain.
- [COMMAND_EXECUTION]: To perform the audit, the skill invokes a wide array of CLI tools and package managers including git, npm, npx, pip-audit, ruff, cargo, and golangci-lint. These operations are within the expected scope of an audit tool but represent a significant level of interaction with the local environment.
Audit Metadata