The Agent Skills Directory

[SAFE]: The skill's primary function is code auditing through local file system analysis. It uses standard tools like ripgrep (rg), find, and wc to search for technical debt indicators.
[COMMAND_EXECUTION]: The bash scripts provided (scripts/find-todos.sh and scripts/scan-large-files.sh) perform read-only operations on the project source code. They utilize safe shell practices (set -eo pipefail) and do not attempt to gain elevated privileges or execute arbitrary code from external sources.
[DATA_EXFILTRATION]: There are no network-capable commands or functions (such as curl or fetch) present in the skill files. All analyzed data remains within the local environment.
[PROMPT_INJECTION]: The SKILL.md file contains standard instructional content for a code quality workflow and does not contain any patterns associated with role-play bypasses or safety guideline overrides.

techdebt-scan