tushare-cli-rust
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [PROMPT_INJECTION]: Aggressive steering instructions in the YAML frontmatter mandate the use of this skill for any query related to Chinese financial markets, potentially overriding the agent's native intent-matching logic.
- [COMMAND_EXECUTION]: The skill relies on the execution of a binary at
~/.claude/skills/tushare-cli/scripts/tushareand recommends using shell utilities likeawkandtailto perform technical analysis calculations via command-line pipes. - [CREDENTIALS_UNSAFE]: The skill provides user instructions for setting the
TUSHARE_TOKENenvironment variable. While standard for API interaction, this requires handling sensitive credentials within the agent's environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external content.
- Ingestion points: Interfaces such as
news,anns_d(announcements), andresearch_reportretrieve long-form text from external market sources. - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions embedded within the retrieved data.
- Capability inventory: The agent can execute subprocesses via the provided binary and standard system shell utilities.
- Sanitization: Absent. There is no specified logic for sanitizing or escaping content retrieved from the Tushare API before it is presented to the agent.
Audit Metadata