The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from several local files which could potentially contain malicious instructions meant to influence the agent's behavior.
Ingestion points: Reads CLAUDE.md, .harness/memory.md, .harness/conventions.md, .harness/rules.md, .harness/constraints.md, archive files, tasks.md, and ACCEPTANCE.md from the project directory.
Boundary markers: None identified. The skill instructs the agent to read and follow the non-negotiables and conventions found in these files.
Capability inventory: The skill performs file read operations and directory listings using ls. It does not include network operations, file writing, or administrative shell execution.
Sanitization: The skill does not perform sanitization or validation of the content within the project files before ingestion.

context-loader