The Agent Skills Directory

[COMMAND_EXECUTION]: The workflow in SKILL.md instructs the agent to use the curl -k command to bypass SSL/TLS certificate validation errors. This is a dangerous practice that leaves the connection open to Man-in-the-Middle (MitM) attacks. The skill also uses lynx via shell piping to process retrieved content.
[EXTERNAL_DOWNLOADS]: The skill retrieves data from multiple third-party domains listed in references/calendars.md, which creates a dependency on external, unverified content.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection from the external websites it scrapes.
Ingestion points: External event calendars listed in references/calendars.md.
Boundary markers: Absent; no delimiters are used to separate fetched content from instructions.
Capability inventory: The agent uses webfetch and command execution (curl, lynx) in SKILL.md.
Sanitization: Absent; the skill does not sanitize or validate the external text before processing it.

ostergotland-events