The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests data from external sources (GitHub issues via analyze-issue) to generate content.
Ingestion points: analyze-issue output processed in SKILL.md.
Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested issue analysis.
Capability inventory: The agent has the ability to create directories (mkdir -p) and write files to the local filesystem.
Sanitization: No sanitization or validation of the input data is performed before it is used to drive the PRD generation process.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and filesystem operations.
Evidence: Explicit instruction to run mkdir -p issues/{ISSUE_NUMBER} in SKILL.md.
Evidence: Instruction to write generated PRD content to issues/{ISSUE_NUMBER}/prd.md.

generate-prd