The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is instructed to ingest and analyze untrusted data from external sources.
Ingestion points: The skill uses web_fetch to retrieve content from live URLs and Read/Grep/Glob to analyze local codebase files (SKILL.md).
Boundary markers: The instructions do not include boundary markers or explicit warnings to treat external content solely as data and ignore any embedded instructions.
Capability inventory: The skill is configured with powerful tools including Bash (shell access), web_fetch (network access), and Write (file system modification).
Sanitization: There is no mention of sanitization or validation of the data retrieved from external URLs or local files before it is processed by the agent.

design-md