chenhao-limit-up
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML configuration files. There are no scripts (Python, JavaScript, shell), executables, or binary files included.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external market and sentiment data for analysis.
- Ingestion points: Data enters the agent context through the "Inputs Needed" section in
SKILL.md(financial, technical, policy, and sentiment data). - Boundary markers: None identified in the prompt templates.
- Capability inventory: None. The skill does not request any tools or perform file/network operations.
- Sanitization: None identified.
- Risk assessment: As the skill lacks any capabilities to execute commands, write files, or make network calls, the risk of indirect prompt injection is negligible.
- [EXTERNAL_DOWNLOADS]: The skill contains a standard YouTube search query link in
invest.mdfor educational purposes. This is a well-known service and does not involve downloading executable content. - [METADATA_POISONING]: The metadata in both
SKILL.mdandinvest.mdis consistent with the stated purpose of the skill (A-share market analysis) and contains no deceptive instructions.
Audit Metadata