The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes commands using the GitHub CLI (gh api and gh search) to monitor repository statistics and search for keyword mentions in public issues. These are standard operations for competitive intelligence.
[EXTERNAL_DOWNLOADS]: The skill references monitoring public data from well-known services including GitHub, npm, PyPI, and Archive.org. These references to established technology services are considered standard for the skill's intended purpose and are treated neutrally.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) because it instructs the agent to ingest and analyze untrusted data from external sources such as GitHub issues, social media mentions, and developer forums. 1. Ingestion points: GitHub issue searches (gh search issues) and social listening tool outputs. 2. Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the external data are present. 3. Capability inventory: The skill primarily uses read-only commands for data collection. 4. Sanitization: There is no evidence of sanitization or filtering of the ingested external content.

competitor-tracking