The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it is designed to ingest and act upon untrusted external data.
Ingestion points: The agent is instructed to process user-provided defect descriptions and executable reproduction paths as specified in SKILL.md.
Boundary markers: There are no explicit delimiters or specific instructions provided to the agent to disregard embedded commands within the ingested bug reports or reproduction scripts.
Capability inventory: The skill relies on a suite of external tools for critical operations, including /tdd for behavior testing, /code-review for standards verification, and /pr for creating pull request descriptions, as documented in UPSTREAM.md.
Sanitization: The instructions do not define specific sanitization or validation steps for the input data before it is processed by the agent or delegated to other tools.

pstack-tdd