The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Feishu Bitable APIs, which creates a surface for indirect prompt injection.
Ingestion points: The skill retrieves data from open.feishu.cn via various endpoints including .../records/search, .../fields, and .../tables as documented in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat external data as untrusted or to ignore instructions embedded within the retrieved fields.
Capability inventory: The skill has the ability to perform network requests to the Feishu API and execute a local helper script (./scripts/get_feishu_token.sh).
Sanitization: No specific sanitization or validation logic is defined for the content returned by the API before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the execution of a local shell script to manage authentication tokens.
Evidence: The skill instructions specify that the agent or user should run TOKEN="$(./scripts/get_feishu_token.sh)" to obtain an access token. This executes a script located within the skill's own directory structure (./scripts/).

feishu-bitable