The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (the source code and existing project documentation) to generate its output, creating a surface for indirect prompt injection.
Ingestion points: The skill reads the entire repository, including source code, README.md, docs/, PRD.md, and configuration files during the 'Fase 0 — Relevamiento' step.
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the ingested files are defined in the skill instructions.
Capability inventory: The skill has the capability to write files to the local file system (docs/architecture/, docs/functional/) and execute shell commands via git.
Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is processed by the agent to create documentation.
[COMMAND_EXECUTION]: The skill uses shell commands to manage the git environment for its documentation tasks.
Evidence: It executes git switch, git pull, git fetch, and git worktree commands to isolate documentation work in new branches or worktrees.

fmway-docs