The Agent Skills Directory

[SAFE]: No malicious code patterns, obfuscation, or unauthorized access attempts were identified. The skill's instructions focus entirely on legitimate source code analysis and documentation tasks.
[PROMPT_INJECTION]: The skill performs automated analysis of external, untrusted codebases from GitHub. This functionality inherently possesses a surface for indirect prompt injection, as malicious instructions embedded within a target repository could theoretically attempt to influence the agent's behavior during the distillation process. Evidence of this surface includes the methodology's reliance on reading arbitrary source files (references/find-grep-before-read.md) and recording extracted data into a local knowledge registry (references/capture-registry-record.md). However, this is an expected risk for code analysis tools and is managed through the skill's focused query approach.

code-distill