The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs the agent or user to install the asc-mcp tool from a third-party GitHub repository (zelentsov-dev/asc-mcp) using the mint package manager. This repository is not associated with a known trusted vendor.
[DATA_EXFILTRATION]: The skill requires access to sensitive local configuration files to perform its triage tasks. Specifically, skills/production-triage.md instructs the agent to locate Sentry authentication tokens in the ~/.sentryclirc file. While this is necessary for the skill's primary purpose of Sentry triage, it involves accessing sensitive credential files.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a potential injection surface.
Ingestion points: skills/production-triage.md (Sentry issue data and stack traces), skills/testflight-triage.md (TestFlight feedback and crash logs), and skills/asc-mcp.md (App Store reviews).
Boundary markers: No specific boundary markers or instructions to treat external data as untrusted were found.
Capability inventory: The skill utilizes curl for network requests and executes CLI tools such as xcsym, atos, and xcodebuild for data processing.
Sanitization: No explicit sanitization logic for ingested external content is described.
[COMMAND_EXECUTION]: The skill documentation includes multiple shell commands for checking URL resolution (curl -sI) and performing crash diagnostics (xcsym triage). These commands are standard for development workflows but rely on shell execution.

axiom-shipping