The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the slacrawl tool using go install from a personal GitHub repository (github.com/vincentkoc/slacrawl), which differs from the repository mentioned in the homepage metadata (github.com/openclaw/slacrawl).
[COMMAND_EXECUTION]: The skill relies on executing various shell commands via the slacrawl binary, including system status checks and synchronization routines.
[COMMAND_EXECUTION]: Includes a capability to execute raw SQL queries (slacrawl sql) against the local message database. This pattern presents a risk of data modification or injection if the SQL strings are generated based on untrusted message content.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes Slack message data.
Ingestion points: Message content, threads, and channel archives retrieved via slacrawl search and slacrawl messages in SKILL.md.
Boundary markers: No delimiters or safety instructions are provided to help the agent distinguish between data and system instructions.
Capability inventory: Shell command execution and raw SQL database querying.
Sanitization: No sanitization, escaping, or validation of the retrieved Slack content is performed before it is processed by the agent.

slacrawl