The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from the local codebase and external sources, creating a potential vector for indirect prompt injection attacks.
Ingestion points: Codebase files scanned during edge case analysis (SKILL.md Step 2.5) and research findings retrieved via the WebSearch tool (Step 3).
Boundary markers: The instructions do not specify the use of delimiters or clear directives to the agent to treat ingested content as untrusted or to ignore embedded instructions.
Capability inventory: The skill has access to sensitive tools including Bash (used for grep), Write, Edit, and WebSearch, allowing for potential file modification or external communication if triggered by injected instructions.
Sanitization: No sanitization or filtering logic is provided for the content ingested from the filesystem or web searches.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute grep searches throughout the project directory to identify code patterns related to error handling, deletion strategies, and other implementation details.

prd-planner