asc-crash-triage
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a series of legitimate 'asc' CLI commands used to list and view app metadata, crash reports, and beta feedback. These commands are consistent with the skill's stated purpose of assisting with App Store Connect triage.
- [PROMPT_INJECTION]: The skill processes external data (TestFlight feedback and crash logs) which constitutes a surface for indirect prompt injection.
- Ingestion points: Data is ingested via
asc testflight feedback listandasc testflight crashes listcommands specified inSKILL.md. - Boundary markers: None present; the instructions do not explicitly warn the agent to treat external feedback as untrusted data.
- Capability inventory: The agent utilizes the 'asc' CLI to perform read and download operations based on the IDs retrieved from the initial data ingestion.
- Sanitization: No specific sanitization or filtering logic is described for the content of the feedback or crash reports.
Audit Metadata