The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill attempts to execute an external shell script 'check-update.sh' located two levels above the skill's own directory ('../../'). This represents an untrusted execution pattern as it relies on code existing outside the skill's distribution package.
[COMMAND_EXECUTION]: The preamble section contains a Bash script block designed to run automatically. This includes directory manipulation ('mkdir -p') and file presence checks ('[ -f ]') on the host system, which could be exploited if path variables are manipulated.
[PROMPT_INJECTION]: The skill processes external data which serves as a potential attack surface for indirect prompt injection.
Ingestion points: The skill reads content from 'docs/03-增长迭代/数据报告与用户反馈.md' and 'docs/03-增长迭代/产品路线图.md'.
Boundary markers: None identified; instructions do not contain explicit delimiters or instructions to ignore embedded commands in the source documents.
Capability inventory: The skill has access to the 'Bash' tool for command execution and the 'Write' tool for file system modifications across the repository.
Sanitization: No evidence of input filtering, validation, or escaping for content read from external document files before it is processed by the agent.

pm-iteration