The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources. * Ingestion points: The skill utilizes tools such as firecrawl:firecrawl_scrape to retrieve web content for research and sentry:get_sentry_resource to fetch production error details as described in SKILL.md. * Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the retrieved external content. * Capability inventory: The skill environment allows for shell command execution including git, npm, and ripgrep, alongside access to external API tools. * Sanitization: There is no evidence of filtering or sanitization logic applied to the ingested external data.

debug-error