sentry

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste their Sentry API token and instructs running a command that embeds that token as a literal argument (ruby ... save_token.rb 'PASTED_TOKEN'), which requires the LLM to accept and output the secret verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill routinely calls the Sentry API (base URL https://sentry.io/api/0) and its scripts and SKILL.md explicitly fetch and display issues, events, releases and issue details (user-generated/untrusted content) which the agent is expected to read and that can influence actions such as whether to resolve an issue.