The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from stakeholders and external documentation during the elicitation process.
Ingestion points: Requirements are gathered from stakeholder interviews and document mining (e.g., PDFs, transcripts) as specified in the 'Elicitation Techniques' and 'Workflow Orchestration' sections.
Boundary markers: The skill documentation does not define specific delimiters or instructions for the agent to ignore potentially malicious embedded instructions within the source material.
Capability inventory: The skill utilizes the Write tool to store gathered requirements in local YAML files and the Skill tool for task delegation.
Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed or stored.

elicitation-methodology