performance-optimization
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external performance data which could contain embedded instructions.
- Ingestion points: The skill instructions in SKILL.md direct the agent to analyze external artifacts such as browser performance traces, flame graphs, slow-query logs, and load-test outputs.
- Boundary markers: There are no explicit instructions or delimiters defined in SKILL.md or the referenced handoff-boundaries.md to ensure the agent ignores instructions embedded within ingested telemetry.
- Capability inventory: The skill YAML frontmatter in SKILL.md allows access to high-privilege tools including Bash, Write, and Grep.
- Sanitization: No sanitization or validation logic is specified for the external data artifacts being processed.
Audit Metadata