app-store-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, specifically user-provided app reviews and descriptions, which represents a potential surface for indirect prompt injection. However, the risk is negligible as the skill lacks dangerous capabilities such as network access, file system writes, or shell command execution.
- Ingestion points: Data enters the agent context through the review analysis (
scripts/review_analyzer.py) and metadata optimization (scripts/metadata_optimizer.py) modules. - Boundary markers: No specific delimiters or instructions to ignore embedded commands were found in the processing logic.
- Capability inventory: All scripts use only standard Python libraries and perform local calculations/string manipulations. There are no
subprocess,os.system,eval, or network-request calls (requests,urllib). - Sanitization: The scripts perform basic normalization (lowercase, punctuation removal) for analysis purposes, though not specifically for injection prevention.
Audit Metadata