The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local shell script scripts/detect-forge-cli.sh to identify the repository forge and ensure the correct CLI tool is used. It also utilizes git, gh, and glab for repository management and release creation, within a defined subset of safe commands.
[PROMPT_INJECTION]: The skill ingests user input through the $ARGUMENTS placeholder in SKILL.md, creating a potential surface for indirect prompt injection. 1. Ingestion points: User-provided strings via the $ARGUMENTS variable in SKILL.md. 2. Boundary markers: Absent; arguments are interpolated directly into the task instruction. 3. Capability inventory: Subprocess execution of local scripts and standard developer tools (git, gh, glab), and file system writes to update CHANGELOG.md. 4. Sanitization: No explicit sanitization of the input arguments is documented.

release