The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script from Sentry's official domain.
Evidence: curl https://cli.sentry.dev/install -fsS | bash in SKILL.md.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Sentry CLI via a global npm package installation.
Evidence: npm install -g sentry in SKILL.md.
[COMMAND_EXECUTION]: The skill utilizes the sentry command-line tool to interact with Sentry APIs for authentication, organization/project management, and issue analysis.
Evidence: Extensive use of sentry commands throughout SKILL.md (e.g., sentry auth, sentry project, sentry issue).
[INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by interpolating untrusted user inputs (like slugs and queries) into shell command arguments.
Ingestion points: User-provided values for <org-slug>, <project-slug>, <query>, and <issue-id> are passed to CLI commands in SKILL.md.
Boundary markers: Absent. No specific delimiters or instructions to ignore malicious content within these inputs are provided.
Capability inventory: Commands allow reading/writing to Sentry projects, organizations, and authentication tokens via the network.
Sanitization: Absent. There is no mention of validating or escaping inputs before they are passed to the shell.

sentry-cli