The Agent Skills Directory

[DYNAMIC_EXECUTION]: The Preamble section executes a shell script using a computed path: bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh". Accessing and executing files from parent directories via relative path calculation can lead to the execution of unintended or malicious files if the directory structure is manipulated or the environment is misconfigured.- [INDIRECT_PROMPT_INJECTION]: The skill incorporates content from docs/03-增长迭代/AARRR增长分析报告.md to guide its decision-making process for identifying growth bottlenecks. * Ingestion points: The agent reads untrusted data from a local markdown file in Step 2.1. * Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential commands embedded within the external report. * Capability inventory: The skill possesses Bash, Write, and Read capabilities, which could be abused if the agent obeys malicious instructions in the ingested data. * Sanitization: No validation or sanitization is performed on the content extracted from the report before it is processed by the agent.- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform environment setup, including directory creation (mkdir -p) and shell script execution, which expands the potential impact of other vulnerabilities.

pm-growth