The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the local repository including source code, shell script logic, and command outputs from tests and linters.
Ingestion points: The agent reads outputs from cargo test, rg (ripgrep), shellcheck, and local regression scripts such as tests/installer_regression.sh and install.sh.
Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the code or logs being analyzed.
Capability inventory: The skill utilizes shell execution (via bash, cargo, and rch), file system modifications, and repository exploration.
Sanitization: Absent. The skill operates directly on raw output and file contents without explicit filtering or sanitization.
[COMMAND_EXECUTION]: The skill defines several shell command sequences and script executions for environment setup and verification workflows. These include cargo operations and execution of local shell scripts like install.sh and scripts/skill-smoke.sh.

pi-agent-rust