The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local CLI tools to perform project management tasks, specifically executing openspec list --json to resolve the OpenSpec root directory and the date command for dated file entries. It also performs directory listings using ls. These commands are standard for the skill's purpose as a planning and discovery tool for the OpenSpec framework.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection by ingesting and processing untrusted external documents.\n
Ingestion points: The 'Phase 1: Ingest' instruction explicitly accepts PRDs or product ideas via file paths, pasted text, or conversational input, which is then summarized and stored by the agent.\n
Boundary markers: The instructions do not specify the use of clear delimiters (e.g., XML tags or triple quotes) or negative constraints to prevent the agent from following instructions embedded within the ingested PRD.\n
Capability inventory: The agent has the capability to read the codebase, execute the openspec CLI, and modify project configuration files (config.yaml), which could be targeted by a malicious PRD.\n
Sanitization: No explicit sanitization or validation of the PRD content is performed before it is processed by the LLM.

discovery