The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches the official ASD-STE100 Issue 9 specification PDF from the organization's website (https://www.asd-ste100.org/assets/files/ASD-STE100_ISSUE9.pdf). This download is a required resource for the skill's functionality and originates from a legitimate, domain-specific source.
[COMMAND_EXECUTION]: The skill executes a local shell script (scripts/ste-check.sh) and standard system utilities including curl, pdftotext, and gawk. These are used to manage the dictionary cache and perform deterministic text processing on technical documentation.
[PROMPT_INJECTION]: The skill processes untrusted external data (such as technical manuals, procedures, or merge requests) to perform compliance checks. This ingestion of external content creates a surface for indirect prompt injection.
Ingestion points: Technical content provided by the user for rewriting or checking, processed by the scripts/ste-check.sh tool.
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the source text being checked.
Capability inventory: Local file creation for marked drafts (.marked.md) and rich text processing via gawk scripts.
Sanitization: Absent; the tool parses surface text without specific filtering for embedded LLM instructions.

ste