The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources such as session transcripts, pull request comments, Slack links, and repository logs.
Ingestion points: Identified in SKILL.md as session IDs, transcript paths, thread URLs, PRs, branches, commits, CI runs, issues, Slack links, and pasted summaries.
Boundary markers: The instructions lack specific boundary markers or delimiters for separating external data from agent instructions, though they advise the agent to prioritize the user's original request over summaries provided by other agents.
Capability inventory: The skill possesses the capability to read files, modify source code, and execute verification commands or tests to repair identified gaps.
Sanitization: No explicit sanitization or filtering logic is described for the audited content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The README.md documentation specifies an installation method using an external package from the @agent-native namespace on the NPM registry (npx @agent-native/skills@latest).
[COMMAND_EXECUTION]: In the 'Audit and fix' mode, the skill is instructed to run validation commands and targeted tests to verify implementation changes (SKILL.md).

agent-watchdog