asc-crash-triage
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes TestFlight beta feedback and crash reports, which are untrusted external data sources. A malicious tester could submit feedback containing prompt injection instructions designed to hijack the agent's behavior during the triage process.
- Ingestion points: Data enters the context through
asc testflight feedback list,asc testflight crashes list, andasc performance diagnostics viewas described inSKILL.md. - Boundary markers: The instructions lack delimiters or explicit warnings for the agent to ignore instructions embedded within the feedback or crash signatures.
- Capability inventory: The agent can execute the
ascCLI tool and write files to the local system (e.g.,asc performance download --output ./metrics.json). - Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from App Store Connect before it is processed by the agent.
Audit Metadata