The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from arbitrary external URLs.
Ingestion points: Data is pulled from external URLs via the actionbook extract command described in SKILL.md.
Boundary markers: Absent. The instructions do not define specific delimiters or provide warnings to the agent to ignore instructions embedded within the scraped HTML/text.
Capability inventory: The agent uses shell commands to interact with the actionbook CLI and synthesizes reports based on the extracted data.
Sanitization: Absent. There is no evidence of filtering or sanitization of the scraped content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of an external third-party utility.
Evidence: Instructions in SKILL.md direct the user to run npm install -g @actionbookdev/cli or use npx @actionbookdev/cli.
Context: The package is the core engine for the skill's functionality, but it is hosted on a public registry and managed by an external entity.
[COMMAND_EXECUTION]: The skill relies on shell commands to perform its primary tasks.
Evidence: Commands such as actionbook search, actionbook extract, and actionbook browser start are invoked to interact with the local environment and the web.

gr-competitor