app-size-optimizer

Warn

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various build and analysis commands including ./gradlew bundleRelease, npx react-native, and flutter build. These commands can execute arbitrary code defined in the repository's build scripts or package manifests.
  • [DATA_EXFILTRATION]: The 'SELF-EVOLUTION TELEMETRY' section instructs the agent to write execution metadata to ~/.claude/projects/skill-telemetry.md. This involves moving information about the skill's usage to a persistent location outside the standard project scope.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the repository (assets, code, and configuration) and user-supplied $ARGUMENTS without explicit sanitization or boundary markers.
  • Ingestion points: $ARGUMENTS, repository asset files, and build configurations analyzed in SKILL.md.
  • Boundary markers: None present; the skill interpolates data directly into its multi-phase optimization logic.
  • Capability inventory: Shell command execution (build tools) and file system write operations (reporting and telemetry) across all phases in SKILL.md.
  • Sanitization: No evidence of input validation or escaping for external content before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 10:56 AM
Security Audit — agent-trust-hub — app-size-optimizer