The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands including git status, git log, git branch, and find to gather evidence and reconstruct recent repository activity.
[DATA_EXFILTRATION]: The skill performs public research by querying external services such as X/Twitter, GitHub, and various AI command-line interfaces (Gemini, Codex, Claude) to find engineering patterns and community insights. These network operations are intended for information gathering and are governed by explicit safety rules that prohibit secret exposure and recommend redacting personal context.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted data from external session artifacts, git logs, and project documentation to synthesize its findings.
Ingestion points: SKILL.md (Workflow Step 2) specifies reading session artifacts, git history, and project documentation files.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested content.
Capability inventory: The skill executes shell commands (git, find) and writes reports to the local filesystem.
Sanitization: No explicit sanitization or escaping of the ingested content is described before it is synthesized into reports.

dreaming